activation-engineering

A curated list of resources for activation engineering

Official code for Steering Large Language Models using Conceptors, presented at the NeurIPS 2024 MINT Workshop.

Runtime control of LLM agent behaviors through activation steering vectors. More calibrated than prompting.

🔓 Ablate — directional ablation (abliteration) toolkit for open-source LLMs. Automatic censorship/refusal removal via residual-stream direction ablation, with KL-guided search, an LLM-judge harness, and one-call push to the Hub. pip install ablate-llm

Iterative Sparse Matrix Steering: Closed-Form Subspace Alignment for Multi-Layer LLM Control (No SGD required).

How meaning moves through a transformer - found, traced, and tested across four model scales.

A closed-loop control system for Large Language Models that steers internal activation states in real-time to prevent mode collapse and toxicity