An advanced research institution in Barcelona is seeking a PhD Student for the Mechanistic Interpretability project. This role involves exploring methods in interpretability and developing novel techniques in neural representations. The ideal candidate holds a Master's degree in a relevant field, has programming proficiency in Python, and possesses theoretical knowledge in neural language modeling. This full-time position offers a competitive salary and extensive training opportunities in a collaborative, multidisciplinary environment. #J-18808-Ljbffr