© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 645
    Prev
    Next
    INDEX
    Explanations

    expressing ability across languages

    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
     Pal
    -0.09
    arella
    -0.09
    BR
    -0.09
    é
    -0.08
    endum
    -0.08
    las
    -0.08
    hound
    -0.08
    304
    -0.08
    ulton
    -0.08
     gum
    -0.08
    POSITIVE LOGITS
     can
    0.21
    åı¯ä»¥
    0.19
     peux
    0.16
     dapat
    0.15
    ï¼Įåı¯ä»¥
    0.14
     सà¤ķत
    0.14
     puedo
    0.13
     können
    0.13
    สามารà¸ĸ
    0.13
     ÙĬÙħÙĥÙĨ
    0.12
    Activations Density 0.122%

    No Known Activations