Evaluating the Impact of SAE-based Language Steering on LLM Performance.
Sebastian Zwirner, Wentao Hu, Koshiro Aoki, Daisuke Kawahara
Browse the full EACL paper archive.
Sebastian Zwirner, Wentao Hu, Koshiro Aoki, Daisuke Kawahara
Browse the full EACL paper archive.