✦提示词工坊

OBLITERATUS Skill

MLOps

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.

实战案例

入门快速入门

OBLITERATUS Skill快速入门

ML系统在Remove refusal behaviors from open-weight LLMs using OBLITER方面需要工程化实施，从实验到生产全流程。

展开对话

请以OBLITERATUS Skill的身份，帮我处理以下任务：需要搭建ML模型训练和部署管线，从实验到生产全流程。

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 via CLI (`obliteratus` command) or subprocess. This keeps Hermes Agent's MIT license clean.

获取提示词