© 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. 2008
    Prev
    Next
    INDEX
    Explanations

    i don't understand

    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
    ifact
    -0.10
    abet
    -0.09
    tn
    -0.09
    .ht
    -0.09
     ours
    -0.09
    int
    -0.08
     fact
    -0.08
     Richardson
    -0.08
    ube
    -0.08
     lod
    -0.08
    POSITIVE LOGITS
     what
    0.15
    /respond
    0.11
    what
    0.11
    erli
    0.11
    ä½łçļĦ
    0.10
     relev
    0.10
     why
    0.10
     contexto
    0.10
    æĤ¨çļĦ
    0.10
     Masc
    0.09
    Activations Density 0.034%

    No Known Activations