Official code for Steering Large Language Models using Conceptors, presented at the NeurIPS 2024 MINT Workshop.
-
Updated
Mar 13, 2025 - Jupyter Notebook
#
model-steering
Here are 7 public repositories matching this topic...
Official implementation of "CSKS: Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models" (EMNLP 2025)
-
Updated
Aug 30, 2025 - Python
Policy-enforcing inference for open-weight LLMs. Self-hosted and OpenAI-compatible: enforces your policy at the residual-stream level, so it survives obfuscation, role-play and jailbreak wrappers. Byte-for-byte no-op on in-policy requests.
jailbreak inference self-hosted ai-safety guardrails llm ai-governance prompt-injection llama-cpp llm-security local-llm gguf openai-compatible model-steering open-weight-models
-
Updated
Aug 5, 2026
Guided undergraduate notebooks on diffusion, flow matching, deterministic sampling, and post-hoc generative-model steering, with a validated CIFAR-10 EDM bridge.
jupyter-notebook generative-models diffusion-models machine-learning-education flow-matching model-steering
-
Updated
Aug 22, 2026 - Jupyter Notebook
Lobopy is a lightweight PyTorch/HuggingFace library for analysing, steering/abliteration of causal language models.
-
Updated
Feb 25, 2026 - Python
Goodfire — independent third-party profile of a public API surface, by API Evangelist. Goodfire is an AI interpretability research lab building tools to understand, debug, and intentionally design neural networks by surfacing the internal features (via sparse autoencoders) that drive model behavior.
machine-learning company research inference artificial-intelligence developer-tools interpretability apis-json llm model-steering
-
Updated
Sep 4, 2026
Envariant — independent third-party profile of a public API surface, by API Evangelist. Envariant is building the control layer for foundation models — an AI interpretability SDK that lets teams inspect, steer, and control model behavior. The SDK exposes a compact set of primitives: detect and causally trace behaviors like hallucinations or invaria
machine-learning company sdk artificial-intelligence developer-tools ai-safety interpretability apis-json foundation-models llm hallucination-detection model-steering
-
Updated
Sep 4, 2026
Add this topic to your repo
To associate your repository with the model-steering topic, visit your repo's landing page and select "manage topics."