Obliteratus

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

raphaelmansuy Updated 94 repo stars
Architecture

File contents

raphaelmansuy/edgecrab commit 19b2778388

Frequently asked questions

npx get-skill add raphaelmansuy/obliteratus