Vol-4146⫷ Vol-4147 ⫸Vol-4148
urn:nbn:de:0074-4147-0


Vol-4147/paper12⫷Vol-4147/paper13⫸Vol-4147/paper14
Katharina SimbeckMariam Mahran

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models