© 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. 61609
    Prev
    Next
    INDEX
    Explanations

    letters J, U, and W

    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
     klu
    -0.10
    kee
    -0.09
     Dunn
    -0.09
    ниÑĤи
    -0.09
    виг
    -0.09
    .::.::
    -0.09
    zza
    -0.09
    ROLLER
    -0.09
    lek
    -0.09
    TRIES
    -0.09
    POSITIVE LOGITS
     dig
    0.13
     voiced
    0.12
     conson
    0.11
    dig
    0.11
     acute
    0.10
     Thorn
    0.10
     sounds
    0.10
     aspir
    0.10
    acute
    0.10
    اءات
    0.09
    Activations Density 0.074%

    No Known Activations