© 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. 23148
    Prev
    Next
    INDEX
    Explanations

    seek professional help if/from

    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
    udi
    -0.10
     cork
    -0.09
    ãĥªãĥ¼ãĤº
    -0.09
    Ñīим
    -0.09
     Citizen
    -0.09
     Meadows
    -0.09
    quir
    -0.09
    isa
    -0.08
    917
    -0.08
    (Source
    -0.08
    POSITIVE LOGITS
     from
    0.18
     från
    0.13
    à¸Īาà¸ģ
    0.12
     professional
    0.12
     từ
    0.12
    from
    0.11
     dari
    0.10
     professionals
    0.10
     profesyonel
    0.10
    readcrumbs
    0.09
    Activations Density 0.014%

    No Known Activations