OBLITERATUS Skill

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,

Source: github.com/NousResearch/hermes-agent/tree/main/skills/mlops/inference/obliteratus · License: MIT