© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30272
    Prev
    Next
    INDEX
    Explanations

    kindness empathy compassion understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensa
    -0.10
     courte
    -0.09
    ublic
    -0.09
    جاد
    -0.09
    (gc
    -0.09
     gracious
    -0.09
     goodwill
    -0.08
    ahoo
    -0.08
     qu
    -0.08
    .Dictionary
    -0.08
    POSITIVE LOGITS
     concern
    0.17
     understanding
    0.15
     consideration
    0.15
    åħ³
    0.12
    Concern
    0.12
     Concern
    0.11
     helpful
    0.11
     Understanding
    0.10
    kind
    0.10
     inclusion
    0.10
    Activations Density 0.070%

    No Known Activations