A curated list of resources for activation engineering

Behavioral auditing & repair toolkit for LLMs. Measures 8 dimensions via confidence probes.

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

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

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

A feature-decoupling Transformer architecture that factorizes word embeddings into Signal Basis × Recipe, achieving native interpretability with emergent semantic organization, 11% natural sparsity, and signal-level causal traceability — without sacrificing language modeling performance.