arxiv:2606.13603
📚 Learning new things
Gabriele Sarti
AI & ML interests
Interpretability for generative language models
Recent Activity
upvoted a collection about 21 hours ago
sandbagging liked a model 3 days ago
harness-hub/Qwen3.8-27B-pi-adapted liked a dataset 9 days ago
edinburgh-dawg/face-eval