© 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. 57532
    Prev
    Next
    INDEX
    Explanations

    playful nature or personality

    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
     beaut
    -0.12
     Beaut
    -0.11
     hilar
    -0.11
    551
    -0.10
     hilarious
    -0.09
    etler
    -0.09
    EMPLARY
    -0.09
    orage
    -0.09
    etting
    -0.09
     synd
    -0.09
    POSITIVE LOGITS
    /play
    0.12
    fully
    0.12
     nature
    0.12
     spirit
    0.12
    y
    0.11
    fulness
    0.11
    grim
    0.10
    yy
    0.10
    ity
    0.10
    -ser
    0.10
    Activations Density 0.038%

    No Known Activations