Guided tutorials and faithful paper replications to get oriented.
A worked tutorial: find a structured concept hiding in a model's activations, prove it is real, and steer the model along it — on the seven days of the week in Llama-3.1-8B.
A general-purpose sparse autoencoder that turns Qwen3-4B into a browsable atlas of 40,960 labeled concepts
A faithful replication that reads bacterial phylogeny out of a genomic model's embeddings