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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44651
    Prev
    Next
    INDEX
    Explanations

    yayılım ğağılımı

    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
     ulaÅŁ
    -0.15
     KiÅŁ
    -0.13
     Bütün
    -0.11
     sayılı
    -0.11
     İst
    -0.11
     kurtul
    -0.11
     Åŀu
    -0.11
     Söz
    -0.11
    lardır
    -0.10
     yapıyor
    -0.10
    POSITIVE LOGITS
     ve
    0.15
     ile
    0.13
     пÑĢоÑĦеÑģÑģионалÑĮ
    0.11
    asyon
    0.10
    981
    0.10
     Ve
    0.10
    ÅĻeh
    0.09
    anda
    0.09
    baz
    0.09
    .yang
    0.09
    Activations Density 0.071%

    No Known Activations