© 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. 26364
    Prev
    Next
    INDEX
    Explanations

    paints and chemicals

    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
     paintings
    -0.17
     painter
    -0.17
     paints
    -0.16
     painters
    -0.15
     painting
    -0.13
    ï¼¹
    -0.12
     Painter
    -0.12
     paint
    -0.12
    Painter
    -0.11
    paint
    -0.11
    POSITIVE LOGITS
     sculpture
    0.13
     var
    0.12
     Sculpt
    0.12
     sculptures
    0.11
    -var
    0.11
    ties
    0.10
    orna
    0.09
     lac
    0.09
    eger
    0.09
    entine
    0.09
    Activations Density 0.031%

    No Known Activations