© 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. 55329
    Prev
    Next
    INDEX
    Explanations

    adhesion molecule ICAM

    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
    rosso
    -0.11
     dá»ĭ
    -0.09
     Justice
    -0.08
    utzer
    -0.08
     fan
    -0.08
     nucle
    -0.08
    iyi
    -0.08
     Wyn
    -0.08
    /Foundation
    -0.08
     Crown
    -0.08
    POSITIVE LOGITS
     cad
    0.19
     ad
    0.16
     Cad
    0.16
    cad
    0.16
     contact
    0.15
    Cad
    0.15
     cave
    0.15
     integr
    0.15
     Eph
    0.14
     adhesive
    0.14
    Activations Density 0.024%

    No Known Activations