[ICLR 2025] General-purpose activation steering library
-
Updated
Sep 18, 2025 - Python
#
activation-steering
Here are 79 public repositories matching this topic...
KV Cache Steering for Inducing Reasoning in Small Language Models
reasoning kv-cache large-language-models llm representation-engineering activation-steering reasoning-language-models cache-steering
-
Updated
Jul 24, 2025 - Python
OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope
transformers interpretability openai-api llm mechanistic-interpretability activation-steering logit-lens jacobian-lens
-
Updated
Aug 3, 2026 - Python
Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope + hidden-directions.
interpretability ai-agents llm mechanistic-interpretability representation-engineering activation-steering jacobian-lens
-
Updated
Aug 3, 2026 - Python
[ACL 2026] - Official repo for the paper: "Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection"
-
Updated
May 22, 2026 - Jupyter Notebook
Activation steering and trait monitoring for HuggingFace transformers
python ai transformers interpretability huggingface llm representation-engineering activation-steering
-
Updated
Jul 20, 2026 - Python
[Under Review] Not All Tokens Are Equally Useful for Steering: Robust Directions and Prefix Steering
mechanistic-interpretability representation-engineering llm-interpretability activation-steering llm-steering robust-dim prefix-steering
-
Updated
Jul 22, 2026 - Python
A bilingual awesome list for refusal suppression research: benchmarks, papers, tools, models, and ecosystem updates.
awesome-list activation-steering over-refusal refusal-suppression safety-neurons safety-degradation evading-safety-alignment
-
Updated
Jun 12, 2026
[ICLR 2026] ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
-
Updated
Sep 30, 2025 - Python
Official code for "Activation Steering for Accent Adaptation in Speech Foundation Models" (Interspeech 2026). Parameter-free accent adaptation via mean-shift steering vectors — no weight updates, consistent WER reductions across 8 accents.
speech-recognition whisper asr interspeech accent-adaptation representation-engineering activation-steering qwen2-audio
-
Updated
Mar 17, 2026 - Python
GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs
-
Updated
Jun 21, 2026 - Python
Does concept-injection introspection emerge with scale? A faithful, controlled reproduction charted across model-size ladders.
open-source research reproduction interpretability llm mechanistic-interpretability activation-steering
-
Updated
Jul 31, 2026 - Python
🏆[ICML 2026 Spotlight] Official implementation of "DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions"
protocol large large-language-models mechanistic-interpretability activation-steering prefill-decode
-
Updated
Jun 21, 2026 - Python
The paper list related to activation steering
-
Updated
May 10, 2026
Steer2Adapt: data-efficient inference-time LLM adaptation by composing steering vectors via Bayesian optimization over a semantic prior subspace.
bayesian-optimization llm representation-engineering activation-steering llm-adaptation steering-vectors
-
Updated
Jun 30, 2026 - Python
Steering vectors with receipts: make one, catch one, deploy a calibrated one. pip install hidden-directions
ai-safety interpretability llm mechanistic-interpretability representation-engineering activation-steering model-auditing
-
Updated
Aug 3, 2026 - Python
CUDA-graph-safe per-request activation steering plugin for vLLM. pip install hotwire-vllm
triton interpretability mechanistic-interpretability vllm llm-inference activation-steering steering-vectors cuda-graphs
-
Updated
Aug 3, 2026 - Python
Phase-aware LLM activation steering and linear probing. A memory-efficient, practical implementation of Representation Engineering (RepE) for safety research.
transformers pytorch ai-safety mechanistic-interpretability llm-safety representation-engineering activation-steering linear-probes
-
Updated
Apr 1, 2026 - Python
Reproduce Emotion Concepts and their Function in a Large Language Model on Qwen 3.6 27b.
ai-safety transformer-interpretability emotion-representation large-language-models llm mechanistic-interpretability ai-interpretability activation-steering functional-emotions emotion-probe
-
Updated
Jul 24, 2026 - Python
Accepted at 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026
-
Updated
Jan 18, 2026 - Python
Improve this page
Add a description, image, and links to the activation-steering topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the activation-steering topic, visit your repo's landing page and select "manage topics."