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.

agentic-in Updated 586 repo stars
Elephant Agent follows a personal path with people, places, risks, rhythms, decisions, and a Personal Model

File contents

agentic-in/elephant-agent commit e3d6632df3

Frequently asked questions

npx get-skill add agentic-in/obliteratus