© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30712
    Prev
    Next
    INDEX
    Explanations

    word origins, numbers, or punctuation

    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
    printStats
    -0.11
    chartInstance
    -0.10
    matchCondition
    -0.09
    styleType
    -0.08
    ="{!!
    -0.08
    <|begin_of_text|>
    -0.07
    fillType
    -0.07
    aml
    -0.07
     noqa
    -0.06
    jÃŃž
    -0.06
    POSITIVE LOGITS
     âĢIJ
    0.07
     intimid
    0.07
     suce
    0.07
     &#8203;&#8203;
    0.07
     <![
    0.07
    :both
    0.07
    ówn
    0.07
    isOpen
    0.07
     ?",
    0.07
    RunWith
    0.06
    Activations Density 0.371%

    No Known Activations