© 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. 2462
    Prev
    Next
    INDEX
    Explanations

    web socket connections

    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
     Wyn
    -0.11
    .avi
    -0.10
    //{{
    -0.10
     Chick
    -0.09
    æŁĶ
    -0.09
    STACK
    -0.09
    PostalCodes
    -0.09
    ÑĤаки
    -0.09
     sne
    -0.09
    VisualStyle
    -0.09
    POSITIVE LOGITS
     WS
    0.21
     ws
    0.20
    ws
    0.18
    WS
    0.17
    .ws
    0.16
    (ws
    0.15
    pong
    0.15
    Ws
    0.14
     upgrade
    0.13
    Upgrade
    0.13
    Activations Density 0.032%

    No Known Activations