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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44919
    Prev
    Next
    INDEX
    Explanations

    realistic models, data visualization, linear equations, missing teeth, game engine, hackintosh

    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
     %[
    -0.08
     ragaz
    -0.08
    ãĥ»ãĥ»ãĥ»\n\n
    -0.07
     (*((
    -0.07
    :č\nč\n
    -0.07
     âĹij
    -0.06
     #__
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    ・・
    -0.06
    gnore
    -0.06
    POSITIVE LOGITS
    .wp
    0.08
           \n\n
    0.07
    WithOptions
    0.07
    âͬ
    0.07
            \n    \n
    0.07
    ?#
    0.06
    .SQL
    0.06
    //===
    0.06
     завиÑģим
    0.06
    âĻª
    0.06
    Activations Density 6.493%

    No Known Activations