2 results found Sort:

stanfordnlp
axbench stanfordnlp
5
62
apache-2.0
3
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
intervention llm-steering interpretability large-language-models mechanistic-interpretability
Created 2024-08-07
399 commits to main branch, last one 4 days ago
IBM
activation-steering IBM
6
54
apache-2.0
2
General-purpose activation steering library
refusal steering alignment llm-steering activation-steering representation-engineering
Created 2024-08-23
37 commits to main branch, last one 2 months ago