Hermes Agent · Built-in

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.

MlopsBuilt-inv2.0.0MIT

What this skill is

This directory page tracks a Hermes-compatible skill reference and links back to the original source for install instructions, files, and updates.

Tags and platforms

AbliterationUncensoringRefusal-RemovalLLMWeight-ProjectionSVDMechanistic-InterpretabilityHuggingFaceModel-Surgery

Featured

Your product here

Show your offer to OpenClaw operators and AI builders across every page and blog.

Advertise