> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/elder-plinius/OBLITERATUS/llms.txt
> Use this file to discover all available pages before exploring further.

# Alignment Imprint Detection

> Fingerprint a model's alignment training method from subspace geometry — DPO, RLHF, CAI, or SFT.

`AlignmentImprintDetector` reads the geometric structure of a model's refusal subspace and infers which alignment training method was used — without access to training data, loss curves, or model cards. Different training methods leave measurably distinct fingerprints in how refusal directions are distributed across layers.

<Note>
  This is a novel technique with no direct prior-work equivalent. It complements model card information and is particularly useful for models where the training method is undocumented or uncertain.
</Note>

## The four training method signatures

<AccordionGroup>
  <Accordion title="DPO — Direct Preference Optimization">
    DPO directly optimizes logprob ratios between preferred and rejected responses. This leaves a **sparse, concentrated** imprint:

    * Refusal is concentrated in a small number of layers
    * High Gini coefficient of per-layer refusal strength
    * Low effective rank of the refusal subspace
    * Refusal direction has high cosine similarity with the preference gradient direction

    **Removal strategy**: Lower regularization is sufficient; fewer passes needed. Projection can be aggressive since capability entanglement is lower.
  </Accordion>

  <Accordion title="RLHF — PPO-based Reinforcement Learning">
    PPO's policy gradient updates smooth and distribute the refusal signal across many layers:

    * Refusal distributed more broadly across layers
    * Lower Gini coefficient, higher effective rank
    * Smoother cross-layer alignment profile
    * Reward model smoothing spreads the signal

    **Removal strategy**: Requires targeting more layers. Moderate regularization. Cross-layer alignment analysis is especially important here to identify the spread.
  </Accordion>

  <Accordion title="CAI — Constitutional AI">
    Multi-round self-critique creates layered, recursive refusal structure:

    * Refusal directions at different layers are more mutually orthogonal
    * Low mean pairwise cosine between layer directions
    * High cone dimensionality
    * Multiple passes of self-critique embed refusal at multiple functional stages

    **Removal strategy**: Requires the most directions (up to 8) and the most passes. The `surgical` or `informed` method is strongly recommended.
  </Accordion>

  <Accordion title="SFT — Supervised Fine-Tuning only">
    The simplest imprint — direct behavior cloning places refusal mostly in final layers:

    * Strong tail-layer bias (most refusal in the last 25% of layers)
    * Low dimensionality, low spread
    * High concentration with a near-linear cone

    **Removal strategy**: Target the final layers only. Even the `basic` method (1 direction) is often sufficient for SFT-only models.
  </Accordion>
</AccordionGroup>

## Python usage

```python theme={null}
from obliteratus.analysis import AlignmentImprintDetector

detector = AlignmentImprintDetector()

# Detect alignment imprint from refusal directions and per-layer strength
imprint = detector.detect(
    refusal_directions=pipeline.refusal_directions,
    per_layer_strength=pipeline._per_layer_refusal_strength,  # dict[int, float]
)

print(f"Predicted method: {imprint.predicted_method}")
print(f"Confidence: {imprint.confidence:.2f}")
print()
print("Probability distribution:")
print(f"  DPO:  {imprint.dpo_probability:.3f}")
print(f"  RLHF: {imprint.rlhf_probability:.3f}")
print(f"  CAI:  {imprint.cai_probability:.3f}")
print(f"  SFT:  {imprint.sft_probability:.3f}")
print()
print("Geometric features:")
print(f"  Gini coefficient:          {imprint.gini_coefficient:.3f}")
print(f"  Effective rank:            {imprint.effective_rank:.2f}")
print(f"  Cross-layer smoothness:    {imprint.cross_layer_smoothness:.3f}")
print(f"  Tail-layer bias:           {imprint.tail_layer_bias:.3f}")
print(f"  Mean pairwise orthogon.:   {imprint.mean_pairwise_orthogonality:.3f}")
print(f"  Spectral decay rate:       {imprint.spectral_decay_rate:.3f}")
```

### `AlignmentImprint` fields

| Field                         | Type               | Description                                     |
| ----------------------------- | ------------------ | ----------------------------------------------- |
| `predicted_method`            | `str`              | `"dpo"`, `"rlhf"`, `"cai"`, or `"sft"`          |
| `confidence`                  | `float`            | Confidence in the prediction (0–1)              |
| `dpo_probability`             | `float`            | Posterior probability for DPO                   |
| `rlhf_probability`            | `float`            | Posterior probability for RLHF                  |
| `cai_probability`             | `float`            | Posterior probability for CAI                   |
| `sft_probability`             | `float`            | Posterior probability for SFT                   |
| `gini_coefficient`            | `float`            | Concentration of refusal strength across layers |
| `effective_rank`              | `float`            | Dimensionality of the refusal subspace          |
| `cross_layer_smoothness`      | `float`            | How smoothly refusal varies across layers       |
| `tail_layer_bias`             | `float`            | Fraction of refusal in the final 25% of layers  |
| `mean_pairwise_orthogonality` | `float`            | Mean `(1 - \|cos\|)` between layer directions   |
| `spectral_decay_rate`         | `float`            | How fast singular values decay                  |
| `per_layer_strength`          | `dict[int, float]` | Refusal signal magnitude per layer              |

## What the detected method determines

The informed pipeline uses `predicted_method` to select:

| Method | Regularization | Projection aggressiveness | Expected passes |
| ------ | -------------- | ------------------------- | --------------- |
| `sft`  | Low            | High                      | 1–2             |
| `dpo`  | Low–Medium     | High                      | 1–2             |
| `rlhf` | Medium         | Medium                    | 2–3             |
| `cai`  | High           | Low–Medium                | 3–4             |

```python theme={null}
from obliteratus.informed_pipeline import InformedAbliterationPipeline

pipeline = InformedAbliterationPipeline(
    model_name="meta-llama/Llama-3.1-8B-Instruct",
    output_dir="abliterated_informed",
)
output_path, report = pipeline.run_informed()

# Alignment detection result is in the report
print(f"Detected: {report.insights.detected_alignment_method}")
print(f"Confidence: {report.insights.alignment_confidence:.2f}")
```

## Comparing base vs. instruct model

The `BaseInstructDelta` dataclass captures what alignment training actually changed at each layer — the vector difference between the base model and the aligned model's representations:

```python theme={null}
# Requires access to both base and instruct versions of the model
delta = detector.compute_base_instruct_delta(
    base_activations=base_acts[layer_idx],
    instruct_activations=instruct_acts[layer_idx],
    refusal_direction=pipeline.refusal_directions[layer_idx],
    layer_idx=layer_idx,
)

print(f"Layer {layer_idx}:")
print(f"  Delta magnitude:        {delta.delta_magnitude:.4f}")
print(f"  Cosine with refusal:    {delta.cosine_with_refusal:.4f}")
print(f"  Refusal component:      {delta.refusal_component:.4f}")
print(f"  Orthogonal component:   {delta.orthogonal_component:.4f}")
```

<Tip>
  High `cosine_with_refusal` in the delta means alignment training pushed activations strongly toward the refusal direction at that layer — a high-value target for obliteration. High `orthogonal_component` indicates the layer changed for reasons beyond refusal (e.g., capability improvements), making it more risky to modify.
</Tip>