CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection Paper • 2508.12535 • Published Aug 18, 2025 • 2
Running 56 Bringing paper to life: A modern template for scientific writing 📝 56 Explore and download a modern scientific paper template
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies Paper • 2506.17673 • Published Jun 21, 2025 • 7