© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61549
    Prev
    Next
    INDEX
    Explanations

    surprise or positive emotion

    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
    SSF
    -0.11
     Fiat
    -0.09
     Script
    -0.09
     Elias
    -0.09
    .CreateInstance
    -0.09
     entertaining
    -0.08
     Chat
    -0.08
    onu
    -0.08
    obile
    -0.08
     Loch
    -0.08
    POSITIVE LOGITS
     surprise
    0.20
     surprises
    0.17
     Surprise
    0.15
     cooked
    0.13
     acts
    0.13
     deeds
    0.13
     surprised
    0.12
    acts
    0.12
     Acts
    0.12
     comple
    0.12
    Activations Density 0.082%

    No Known Activations