© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8761
    Prev
    Next
    INDEX
    Explanations

    ve ardından

    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
    ırak
    -0.15
     Onun
    -0.14
     ulaÅŁ
    -0.14
     DeÄŁer
    -0.14
     Açık
    -0.14
     Ä°nsan
    -0.14
     Bütün
    -0.13
     MÃ¼ÅŁ
    -0.13
     Bazı
    -0.13
     Söz
    -0.13
    POSITIVE LOGITS
     ve
    0.16
     пÑĢоÑĦеÑģÑģионалÑĮ
    0.14
     Bir
    0.13
     bir
    0.12
     еÑģÑĤе
    0.12
     kim
    0.11
     haz
    0.11
     ı
    0.10
     Dah
    0.10
    Bir
    0.10
    Activations Density 0.090%

    No Known Activations