© 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. 34273
    Prev
    Next
    INDEX
    Explanations

    making actions

    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
     making
    -0.13
     makin
    -0.10
    使
    -0.10
    eru
    -0.09
    making
    -0.09
    [__
    -0.09
     Making
    -0.09
    .intellij
    -0.09
     Measures
    -0.09
    oya
    -0.09
    POSITIVE LOGITS
     happen
    0.20
     rounds
    0.13
    /send
    0.12
     strides
    0.12
    leine
    0.11
    appen
    0.11
     mistakes
    0.11
     progress
    0.11
     Rounds
    0.11
     available
    0.11
    Activations Density 0.128%

    No Known Activations