© 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. 62709
    Prev
    Next
    INDEX
    Explanations

    yardımcı olmak, emin olmak, tavsiye etmek

    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
     oldukları
    -0.14
     almaktadır
    -0.13
     MÃ¼ÅŁ
    -0.12
     olduk
    -0.12
     olduÄŁuna
    -0.12
     alınması
    -0.12
    lediÄŁi
    -0.12
     olacaÄŁ
    -0.12
     Hiç
    -0.11
     alıyor
    -0.11
    POSITIVE LOGITS
     ve
    0.17
     ol
    0.12
     Ve
    0.11
    ̧
    0.11
     Ol
    0.10
    olas
    0.10
     ers
    0.10
     ed
    0.10
    alar
    0.10
    Haz
    0.09
    Activations Density 0.089%

    No Known Activations