© 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. 59950
    Prev
    Next
    INDEX
    Explanations

    what asks a question

    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
    asso
    -0.08
    лÑİ
    -0.08
     spat
    -0.08
     rog
    -0.08
     dataIndex
    -0.08
    ​​
    -0.08
     metab
    -0.08
    HttpRequest
    -0.08
    anje
    -0.08
     shrinking
    -0.08
    POSITIVE LOGITS
     call
    0.13
    (call
    0.11
    call
    0.10
    alat
    0.10
     gá»įi
    0.10
    ató
    0.09
    .call
    0.09
    ĵåIJį
    0.09
    ¶Į
    0.09
     Fry
    0.08
    Activations Density 0.027%

    No Known Activations