concept
active
concept:wellbeing-probe-sad-vs-happyWellbeing probe (sad vs. happy)
One of four emotive concept probes trained; contrastive pair sad/happy with best layer 16 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 wellbeing 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.
- One of four emotive concept probes trained; contrastive pair bored/interested with best layer 14 in LLaMA-3.2-3B
- Documented outcome of practices diminishing sense of self; measured effect of self-illusion awareness.
- Organization that made the article open access.
- Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
- The experiential measure of life; a living process is congruent with and governed by feeling, and the feeling a place presents is the measure of its life.
- Alexander distinguishes 'feeling' — the sense of being part of the ocean, sky, world — from emotions like happiness, sadness, or anger
- Standard linear probing technique; compared to mass-mean probing for classification accuracy and causal implication