© 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. 22503
    Prev
    Next
    INDEX
    Explanations

    convolutional neural networks

    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
    chaft
    -0.09
    atrix
    -0.09
    istrovstvÃŃ
    -0.09
    lfw
    -0.09
     META
    -0.09
     Kunst
    -0.09
     Chall
    -0.09
    主任
    -0.08
    erp
    -0.08
    fad
    -0.08
    POSITIVE LOGITS
    al
    0.18
     neural
    0.14
     layers
    0.12
    ary
    0.12
    (Conv
    0.11
    ixer
    0.11
     Neural
    0.11
    olution
    0.10
     networks
    0.10
     filters
    0.10
    Activations Density 0.022%

    No Known Activations