Directional ablation (abliteration) toolkit for open-source language models: extract, ablate, and optimize the removal of refusal / behavioral directions in the residual stream.
Cross-referenced across 55 tracked directories
#9038
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
7/18/2026
First Seen
Recently added to the ecosystem
Anthropic <[email protected]>
The official Python library for the anthropic API
Magniv
PromptLayer is a platform for prompt engineering and tracks your LLM requests.
Unclecode
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & scraper