ZFancy / awesome-activation-engineering Star 123 Code Issues Pull requests A curated list of resources for activation engineering control concept transparent ai-safety interpretability large-language-models llm llm-aligment activation-engineering concept-rep concept-activation-vector Updated Oct 2, 2025
bassrehab / steering-vectors-agents Star 2 Code Issues Pull requests Runtime control of LLM agent behaviors through activation steering vectors. More calibrated than prompting. machine-learning transformers pytorch steering-behaviors ai-safety interpretability langchain llm-agents activation-engineering steering-vectors contrastive-activation-addition Updated Dec 19, 2025 Python
G-Art / matrix_steering_vector_research Star 2 Code Issues Pull requests Iterative Sparse Matrix Steering: Closed-Form Subspace Alignment for Multi-Layer LLM Control (No SGD required). pytorch alignment interpretability llm activation-engineering steering-vectors Updated Jan 5, 2026 Jupyter Notebook
Jason-Wang313 / RISER Star 0 Code Issues Pull requests A closed-loop control system for Large Language Models that steers internal activation states in real-time to prevent mode collapse and toxicity reinforcement-learning pytorch control-theory ai-safety riser mechanistic-interpretability llm-steering activation-engineering Updated Feb 1, 2026 Python