© 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. 4515
    Prev
    Next
    INDEX
    Explanations

    how followed by a query

    np_acts-logits-general · gemini-2.5-flash-lite

    questions that begin with the word “How.”

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     blas
    -0.10
    ifen
    -0.10
    Inactive
    -0.09
    olk
    -0.09
    ustos
    -0.08
    <|begin_of_text|>
    -0.08
    abee
    -0.08
    azen
    -0.08
    uilder
    -0.08
    inactive
    -0.08
    POSITIVE LOGITS
    dy
    0.17
    itzer
    0.12
     does
    0.11
    ie
    0.11
    ling
    0.11
    ards
    0.11
    beit
    0.11
    ick
    0.10
    DY
    0.10
    /
    0.10
    Activations Density 0.088%

    No Known Activations