method
active
method:injected-thought-introspection-protocolInjected-thought introspection protocol
Inject J-lens vector and ask model to report.
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Experimental paradigm where the model is told about the possibility of thought injection and asked to report detection and identification.
- Models can detect and identify injected concept vectors ~20% of the time at optimal layer/strength in Opus 4.1, with immediacy suggesting internal rather than output-inferred detection.
- Stage 3 of character training: SFT on synthetic introspective data generated by post-distillation checkpoint
- Key gap identified in the literature; systematic self-examination processes for machine consciousness development.
- The ability of a model to observe its own past internal states or computations; claimed to be architecturally permitted by transformers.
- Key quantitative characterization of the layer-dependence of partial introspection
- The capacity of a model to self-report on its internal emotional state when its SAE features are steered, used here as a measurement tool
- Identified gap; methods for enabling machine consciousness development through self-examination.