chore: inject Hugging Face frontmatter metadata dynamically a825f06 GitHub Actions commited on 13 days ago
docs: update readme references and add modular trajectory harvester 848238a sadhumitha-s commited on 13 days ago
feat: redeploy fresh model weights and demo trajectories ef707cc sadhumitha-s commited on 13 days ago
feat: redeploy fresh model weights and demo trajectories 705175b sadhumitha-s commited on 13 days ago
feat: redeploy fresh model weights and demo trajectories 2ec63e1 sadhumitha-s commited on 13 days ago
feat: redeploy fresh model weights and demo trajectories bf82ccb sadhumitha-s commited on 13 days ago
feat: redeploy fresh model weights and demo trajectories ec88753 sadhumitha-s commited on 13 days ago
feat: redeploy fresh model weights and demo trajectories 2c42b88 sadhumitha-s commited on 13 days ago
feat: package model weights, SAE checkpoints, and dynamic trajectories using Git LFS e73506b sadhumitha-s commited on 13 days ago
feat: implement interactive circuit surgery engine, dashboard integration, and Neuronpedia export functionality 33a0021 sadhumitha-s commited on 13 days ago
feat: implement safety auditing tools for steering and deceptive alignment detection 5ccbe34 sadhumitha-s commited on 14 days ago
refactor: implement centralized configuration, upgrade SAE training to multi-layer TopK, and optimize dashboard attribution UX b7ddfc6 sadhumitha-s commited on 16 days ago
revise readme for prereqs and workflow clarity 14d2c06 unverified sadhumitha-s commited on 18 days ago
feat: implement NLA explainer and universality probe and refactor path patching engine 8577352 sadhumitha-s commited on 18 days ago
feat: implement SAE manager for latent decomposition and steering library for contrastive activation addition 0346604 sadhumitha-s commited on 24 days ago