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. 65438
    Prev
    Next
    INDEX
    Explanations

    assistantLu_2.4.2.dmg

    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
     migrationBuilder
    -0.10
     NONINFRINGEMENT
    -0.09
    IRMWARE
    -0.08
    ustos
    -0.08
     èĸ
    -0.08
     '((
    -0.08
    imeType
    -0.08
    '''č\n
    -0.08
    __,__
    -0.08
    _thickness
    -0.07
    POSITIVE LOGITS
     Olsen
    0.09
    ows
    0.09
    owler
    0.08
     Silent
    0.08
    eda
    0.08
    oucher
    0.08
     onFinish
    0.07
     icing
    0.07
    è¾ij
    0.07
     lul
    0.07
    Activations Density 0.134%

    No Known Activations