© 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. 51397
    Prev
    Next
    INDEX
    Explanations

    new champions, youtube video, official documentation

    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
    isNull
    -0.07
    a
    -0.07
     reb
    -0.07
    ormsg
    -0.07
    (
    -0.07
    ...
    -0.07
    ï¼ļ\n
    -0.06
    .addComponent
    -0.06
    ->_
    -0.06
    enci
    -0.06
    POSITIVE LOGITS
    latlong
    0.09
    -wsj
    0.09
    isContained
    0.09
    scriptId
    0.09
    \Bridge
    0.08
    -lnd
    0.08
    $MESS
    0.08
    mPid
    0.08
    WithString
    0.08
    groupon
    0.08
    Activations Density 0.009%

    No Known Activations