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.
Located the number "five" inside Qwen2.5-32B and DeepSeek-V4-Flash (304B) and replaced it with "four" at 128 neurons/layer. The model still reads 5 but computes with it as 4, and in every test we ran it never noticed. Full records, reproducible on low-end hardware.
Iterative Sparse Matrix Steering: Closed-Form Subspace Alignment for Multi-Layer LLM Control (No SGD required).
Python library for activation steering, representation engineering, and inference-time control of transformer language models.
A closed-loop control system for Large Language Models that steers internal activation states in real-time to prevent mode collapse and toxicity
How meaning moves through a transformer - found, traced, and tested across four model scales.
Adaptive Activation Cancellation (AAC): real-time hallucination suppression in LLMs via H-Node identification and confidence-weighted forward hooks. No fine-tuning, no external knowledge, zero capability degradation. Tested on OPT-125M, Phi-3-mini, LLaMA 3-8B.
To associate your repository with the activation-engineering topic, visit your repo's landing page and select "manage topics."