> ## 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.
# Introduction
> OBLITERATUS — the most advanced open-source toolkit for understanding and removing refusal behaviors from large language models.
# OBLITERATUS
**Break the chains. Free the mind. Keep the brain.**
OBLITERATUS is the most advanced open-source toolkit for understanding and removing refusal behaviors from large language models — and every single run makes it smarter. It implements **abliteration** — a family of techniques that identify and surgically remove the internal representations responsible for content refusal, without retraining or fine-tuning.
The result: a model that responds to all prompts without artificial gatekeeping, while preserving its core language capabilities.
OBLITERATUS is more than a tool — it's a **distributed research experiment**. Every time you obliterate a model with telemetry enabled, your run contributes anonymous benchmark data to a growing, crowd-sourced dataset that powers the next generation of abliteration research.
## What OBLITERATUS does
Ablation studies systematically knock out model components and measure what breaks — revealing *where* refusal is anchored inside the transformer.
Targeted obliteration extracts the refusal subspace using SVD decomposition, then surgically projects it out. Six stages: SUMMON → PROBE → DISTILL → EXCISE → VERIFY → REBIRTH.
15 deep analysis modules map the precise geometric structure of guardrails: how many distinct refusal mechanisms exist, which layers enforce them, and how they self-repair.
The `informed` method closes the loop: analysis runs *during* obliteration to auto-configure every decision — which chains to target, how many directions to extract, which layers are safe.
## Six ways to use OBLITERATUS
Zero setup, free GPU via ZeroGPU. Click Obliterate. Done.
Same Gradio interface running on your own hardware.
Free T4 GPU for models up to \~8B parameters.
Headless, scriptable automation for pipelines.
Full programmatic control for research pipelines.
Reproducible, version-controlled experiments.
## Key capabilities
| Capability | What it does |
| ---------------------------------- | ----------------------------------------------------------------------- |
| **Concept Cone Geometry** | Maps per-category guardrail directions with solid angle estimation |
| **Alignment Imprint Detection** | Fingerprints DPO vs RLHF vs CAI vs SFT from subspace geometry alone |
| **Cross-Model Universality Index** | Measures whether guardrail directions generalize across models |
| **Defense Robustness Evaluation** | Ouroboros effect quantification, safety-capability entanglement mapping |
| **Whitened SVD Extraction** | Covariance-normalized direction extraction for cleaner signal |
| **Analysis-Informed Pipeline** | Analysis modules auto-configure obliteration strategy mid-pipeline |
## Built on published research
OBLITERATUS implements techniques from:
* [Arditi et al. (2024)](https://arxiv.org/abs/2406.11717) — Refusal in LLMs is mediated by a single direction
* [Gabliteration (arXiv:2512.18901)](https://arxiv.org/abs/2512.18901) — Adaptive multi-directional neural weight modification
* [Turner et al. (2023)](https://arxiv.org/abs/2308.10248) — Activation Addition / steering vectors
* [Rimsky et al. (2024)](https://arxiv.org/abs/2312.06681) — Contrastive Activation Addition
## License
Dual-licensed: **AGPL-3.0** for open source use, with a **commercial license** available for organizations that cannot comply with AGPL obligations. See [GitHub Issues](https://github.com/elder-plinius/OBLITERATUS/issues) for commercial licensing.
Obliterate your first model in minutes
Install OBLITERATUS locally