© 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. 32361
    Prev
    Next
    INDEX
    Explanations

    belt drive, belted, straps

    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
     sleeve
    -0.12
     Sleeve
    -0.11
     glued
    -0.10
     sleeves
    -0.09
    ãģĹãĤĥ
    -0.09
     pied
    -0.09
    verity
    -0.09
    rupa
    -0.09
    /qu
    -0.09
    hood
    -0.09
    POSITIVE LOGITS
     belt
    0.29
     cin
    0.26
     Belt
    0.25
    belt
    0.24
     belts
    0.24
     waist
    0.20
     Cin
    0.20
     buckle
    0.19
    cin
    0.18
     Buck
    0.17
    Activations Density 0.029%

    No Known Activations