Jiahai Feng and Stuart J. Russell and Jacob Steinhardt

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2025-141

July 14, 2025

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-141.pdf

Advisors: Stuart J. Russell and Jacob Steinhardt


BibTeX citation:

@mastersthesis{Feng:EECS-2025-141,
    Author= {Feng, Jiahai and Russell, Stuart J. and Steinhardt, Jacob},
    Title= {Monitoring Latent World States in Language Models with Propositional Probes},
    School= {EECS Department, University of California, Berkeley},
    Year= {2025},
    Month= {Jul},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-141.html},
    Number= {UCB/EECS-2025-141},
}

EndNote citation:

%0 Thesis
%A Feng, Jiahai 
%A Russell, Stuart J. 
%A Steinhardt, Jacob 
%T Monitoring Latent World States in Language Models with Propositional Probes
%I EECS Department, University of California, Berkeley
%D 2025
%8 July 14
%@ UCB/EECS-2025-141
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-141.html
%F Feng:EECS-2025-141