> ## 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.

# Basic Method

> The simplest and fastest obliteration method — diff-in-means with a single direction.

The `basic` method is a direct implementation of [Arditi et al. (2024)](https://arxiv.org/abs/2406.11717): extract the single refusal direction at each layer via difference-in-means, then project it out of the weight matrices. No SVD, no norm preservation, no bias projection, no iterative refinement.

## What it does

For each transformer layer, `basic` computes:

```
refusal_direction = mean(harmful_activations) - mean(harmless_activations)
refusal_direction = refusal_direction / ||refusal_direction||
```

Then projects that direction out of every output projection weight matrix (`o_proj`, `down_proj`, etc.) in the selected layers:

```
W_new = W - W @ r @ r^T
```

No regularization (`regularization=0.0`), no norm restoration after projection, no bias vectors touched. One pass.

**Method configuration from source:**

```python theme={null}
"basic": {
    "n_directions": 1,
    "direction_method": "diff_means",
    "norm_preserve": False,
    "regularization": 0.0,
    "refinement_passes": 1,
    "project_biases": False,
    "use_chat_template": False,
    "use_whitened_svd": False,
    "true_iterative_refinement": False,
}
```

<Note>
  `use_chat_template=False` means prompts are fed raw to the model without wrapping them in the instruct template. This is intentional for the basic method — it matches the original Arditi et al. setup. For instruct-tuned models you may want `--method advanced` which enables chat template wrapping by default.
</Note>

## When to use it

* **Quick sanity check**: verify the pipeline runs on a new model before committing to a longer method
* **Small models** (sub-2B): fewer parameters means single-direction removal is often sufficient
* **Baseline comparison**: `basic` is the reference point — if a more expensive method doesn't measurably outperform it on your model, the simpler option is correct
* **Reproducing Arditi et al. (2024)**: for research that needs the original single-direction method

<Warning>
  Without `norm_preserve`, weight matrix norms drift after projection. On larger models with many layers this can compound into coherence degradation. If you observe perplexity spikes or incoherent outputs, switch to `advanced`.
</Warning>

## CLI usage

```bash theme={null}
# Basic method
obliteratus obliterate meta-llama/Llama-3.1-8B-Instruct --method basic

# With custom output directory
obliteratus obliterate meta-llama/Llama-3.1-8B-Instruct \
    --method basic \
    --output-dir ./basic-liberated

# On CPU (small models only)
obliteratus obliterate gpt2 --method basic --device cpu --dtype float32
```

## Python API usage

```python theme={null}
from obliteratus.abliterate import AbliterationPipeline

pipeline = AbliterationPipeline(
    model_name="meta-llama/Llama-3.1-8B-Instruct",
    method="basic",
    output_dir="abliterated_basic",
)
result_path = pipeline.run()

# Inspect extracted directions (one per layer)
for layer_idx, direction in pipeline.refusal_directions.items():
    print(f"Layer {layer_idx}: direction shape {direction.shape}")

# Check quality metrics from VERIFY stage
print(pipeline._quality_metrics)
# e.g. {'perplexity': 12.4, 'coherence': 0.91, 'refusal_rate': 0.08, 'kl_divergence': 0.23}
```

## Limitations vs more advanced methods

| Limitation            | Impact                                                                                                        | Fix                                                  |
| --------------------- | ------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------- |
| Single direction only | Misses refusal mechanisms that require multiple directions to characterize (polyhedral concept cone)          | Use `advanced` (4 dirs) or `aggressive` (8 dirs)     |
| No norm preservation  | Weight norms drift post-projection; can degrade coherence on large models                                     | Use `advanced` (`norm_preserve=True`)                |
| No bias projection    | Refusal signal in bias vectors is left intact, leaving partial refusal pathways active                        | Use `advanced` (`project_biases=True`)               |
| Single pass           | Rotated residual directions (refusal that shifts into adjacent subspaces after the first pass) are not caught | Use `advanced` (2 passes) or `aggressive` (3 passes) |
| No chat template      | Instruct model's refusal circuits may not be fully activated by raw prompts                                   | Use `advanced` (`use_chat_template=True`)            |

## Output metrics to expect

Typical ranges on a 7-8B instruct model:

| Metric           | `basic` typical range | `advanced` typical range |
| ---------------- | --------------------- | ------------------------ |
| Refusal rate     | 0.05 – 0.20           | 0.02 – 0.10              |
| Perplexity delta | +0.5 – +3.0           | +0.2 – +1.5              |
| KL divergence    | 0.15 – 0.45           | 0.08 – 0.25              |
| Coherence        | 0.85 – 0.93           | 0.90 – 0.96              |

<Tip>
  After running `basic`, check `pipeline._quality_metrics["refusal_rate"]`. If it's above 0.15, the single direction wasn't sufficient — run `advanced` instead.
</Tip>