Sparse interventions on 8–64 neurons distributed across layers can activate task behavior in instruction-tuned LLMs, outperforming first-order linear steering approaches by modeling nonlinear neuron interactions.
Q: input 1\nA: output1\n\nQ: input2\nA: output2\n\n[...]Q: inputk\nA: outputk\n\nQ: input\nA:
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Distributed Sparse Interventions in Language Models
Sparse interventions on 8–64 neurons distributed across layers can activate task behavior in instruction-tuned LLMs, outperforming first-order linear steering approaches by modeling nonlinear neuron interactions.