Representation Engineering Python Packages

wisent

Monitor and influence AI Brains

saklas

Activation steering and trait monitoring for HuggingFace transformers

steering-vectors

Steering vectors for transformer language models in Pytorch / Huggingface

bitnarrow

Zero-training, in-place weight surgery and directional abliteration engine for 4-bit quantized LLMs using Winsorized activation profiling and Gram-Schmidt orthogonal projection

hidden-directions

Steering vectors with receipts: make one, catch one, deploy a calibrated one. pip install hidden-directions

reprobe

Phase-aware LLM activation steering and linear probing. A memory-efficient, practical implementation of Representation Engineering (RepE) for safety research.