concept
active
concept:interest-probe-bored-vs-interestedInterest probe (bored vs. interested)
One of four emotive concept probes trained; contrastive pair bored/interested with best layer 14 in LLaMA-3.2-3B
Neighborhood — ranked by edge-count
Methods (1)
method
- Contrastive mean-difference probeimplementsProbe construction method: concept vector at each layer is L2-normalized difference between mean positive and mean negative representations from contrastive system prompts
Concepts (1)
concept
- Emotive states in LLMsimplementsDirections in activation space associated with contrastive emotive concept pairs studied in this paper as targets for introspection
Findings (1)
finding
- Probe validation result confirming interest direction captures meaningful structure
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.
- Something that benefits or harms a being; tied to welfare subjectivity.
- One of four emotive concept probes trained; contrastive pair distracted/focused with best layer 10 in LLaMA-3.2-3B
- Active sampling of novel contingencies to minimize uncertainty; formalized as novelty component of expected free energy
- Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
- One of four emotive concept probes trained; contrastive pair impulsive/planning with best layer 13 in LLaMA-3.2-3B
- One of four emotive concept probes trained; contrastive pair sad/happy with best layer 16 in LLaMA-3.2-3B
- The ability of probes trained on one dataset to transfer accurately to topically and structurally different datasets
- Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state