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. 65252
    Prev
    Next
    INDEX
    Explanations

    you today

    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
    Tomorrow
    -0.11
    igma
    -0.10
     Tomorrow
    -0.09
    ous
    -0.09
    appa
    -0.09
    alar
    -0.09
    Sortable
    -0.09
    ingly
    -0.09
    .showError
    -0.08
     sokak
    -0.08
    POSITIVE LOGITS
     today
    0.20
    today
    0.16
    ä»Ĭ天
    0.14
     heute
    0.12
     ÑģегоднÑı
    0.12
     aujourd
    0.11
    ä»ĬæĹ¥
    0.11
     oggi
    0.11
    _today
    0.11
     dnes
    0.11
    Activations Density 0.045%

    No Known Activations