© 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. 36468
    Prev
    Next
    INDEX
    Explanations

    or alternatives

    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
    /or
    -0.12
    actus
    -0.11
    481
    -0.09
    gree
    -0.09
    ìĭ
    -0.09
    ulner
    -0.08
    ampo
    -0.08
    rogen
    -0.08
    .me
    -0.08
    ewan
    -0.08
    POSITIVE LOGITS
    ifice
    0.20
     else
    0.20
     же
    0.19
    phans
    0.18
     worse
    0.16
    ients
    0.16
    ignal
    0.16
     èĢħ
    0.16
     if
    0.16
    ific
    0.16
    Activations Density 0.060%

    No Known Activations