Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65429
    Prev
    Next
    INDEX
    Explanations

    assistant/user delimiters

    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
    .IsNullOr
    -0.09
    ubat
    -0.09
     Beng
    -0.09
    amo
    -0.09
    apy
    -0.09
    GNUC
    -0.08
    à¸µà¸Ł
    -0.08
    utut
    -0.08
    ););\n
    -0.08
     incons
    -0.08
    POSITIVE LOGITS
    kad
    0.09
    ायà¤ķ
    0.09
     Crane
    0.09
     latter
    0.08
     Barcl
    0.08
    ("'"
    0.08
    elt
    0.08
    éĻ¢
    0.08
     usher
    0.08
    //=
    0.08
    Activations Density 0.041%

    No Known Activations