Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety
F. Barez,
T.-Y. Wu,
H. Batra,
G. Dominici,
F. Draye,
Y. Elazar,
D. Fornasiere,
A. García,
A. Harrasse,
R. Harris,
S. Hooker,
M. Lan,
B.Z. Li,
A. Maiwald,
N.F. Oozeer,
N. Saphra,
O.D. Shafran,
A. Simhi,
R. Trager,
S.K. Upadhyay,
Z. Yao,
Y. Zhao,
S.B. Cohen,
M. Geva,
Y. Bengio,
S. Biderman,
H. Sajjad November 2026Publication
arXiv:2611.08438