© 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. 9060
    Prev
    Next
    INDEX
    Explanations

    yazı yayım sayıl

    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
    lÃ¼ÄŁ
    -0.15
     ulaÅŁ
    -0.13
    amı
    -0.12
    kanı
    -0.12
     Ä°nsan
    -0.12
     Bazı
    -0.12
    Ä°n
    -0.12
     KiÅŁ
    -0.11
     kıl
    -0.11
    lÃ¼ÄŁÃ¼
    -0.11
    POSITIVE LOGITS
     ve
    0.16
    lar
    0.13
     Bir
    0.11
    ï¼¾
    0.11
    arda
    0.11
    orman
    0.10
    è°ĭ
    0.10
    ï½Ģ
    0.10
    alt
    0.09
    arl
    0.09
    Activations Density 0.068%

    No Known Activations