Iterative Sparse Matrix Steering: Closed-Form Subspace Alignment for Multi-Layer LLM Control (No SGD required).
-
Updated
Jan 5, 2026 - Jupyter Notebook
#
steering-vectors
Here are 5 public repositories matching this topic...
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
Repository for paper "Understanding (Un)Reliability of Steering Vectors in Language Models" by Joschka Braun, Carsten Eickhoff, David Krueger, Seyed Ali Bahrainian, Dmitrii Krasheninnikov.
-
Updated
Jun 10, 2025 - Jupyter Notebook
Official implementation of "Beyond Multiple Choice: Evaluating Steering Vectors for Summarization" (Findings of EACL 2026).
evaluation summarization language-model abstractive-text-summarization abstractive-summarization steering-vector steering-vectors
-
Updated
Jan 21, 2026 - Python
My first eval / interpretability project. Testing steering vectors for truthfulness and honesty on TruthfulQA and MASK.
-
Updated
Jan 29, 2026 - Python
Improve this page
Add a description, image, and links to the steering-vectors topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the steering-vectors topic, visit your repo's landing page and select "manage topics."