Self-Fulfilling (Mis)alignment: Base Models Collection Here we are, our base model checkpoints. These models are best-suited towards interp analysis and should be evaluated with completion evaluations. • 13 items • Updated Mar 2 • 2
Running Featured 24 Chasing the Counting Manifold in Open LLMs 📚 24 Counting manifolds in open LLMs from behavior to SAEs.
Running 117 The Eiffel Tower Llama 📝 117 Explore the Eiffel Tower Llama experiment with open-source models