OBLITERATUS Skill
Remove refusal behaviors (guardrails) from open-weight LLMs without retraining or fine-tuning. Uses mechanistic interpretability techniques — including diff-in-means, SVD, whitened SVD, LEACE concept erasure, SAE decomposition, Bayesian kernel projection, and more — to identify and surgically excise refusal directions from model weights while preserving reasoning capabilities.
License warning: OBLITERATUS is AGPL-3.0. NEVER import it as a Python library. Always invoke v
[Description truncada. Veja o README completo no GitHub.]