© 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. 51536
    Prev
    Next
    INDEX
    Explanations

    .now, date, time, opts, else, when

    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
     bottoms
    -0.09
    .infinity
    -0.09
     Advent
    -0.08
    ä¿Ĺ
    -0.08
     Fabric
    -0.08
    hn
    -0.08
    .Formatter
    -0.08
     Lug
    -0.08
    ador
    -0.08
    //{{
    -0.08
    POSITIVE LOGITS
    ''''
    0.09
    anko
    0.09
     migrationBuilder
    0.08
    (æ°´
    0.08
    ｿ
    0.08
    SizeMode
    0.08
    گاÙĨ
    0.07
    ãĢĤãĢĤ\n\n
    0.07
    .byId
    0.07
    gens
    0.07
    Activations Density 0.004%

    No Known Activations