Function vectors steer LLMs successfully where the logit lens fails to decode the target answer, showing the two properties come apart.
Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens
Function vectors steer LLMs successfully where the logit lens fails to decode the target answer, showing the two properties come apart.