© 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. 59872
    Prev
    Next
    INDEX
    Explanations

    upcoming in, Environment (, them directly, sudo privileges

    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
    æĪĸèĢħ
    -0.14
    è¿ĺæĺ¯
    -0.12
    /or
    -0.12
    ìĿ´ìŀIJ
    -0.11
     zwar
    -0.11
    або
    -0.10
    ìĿ¸ì§Ģ
    -0.10
    以åıĬ
    -0.10
     или
    -0.09
     oraz
    -0.09
    POSITIVE LOGITS
     depending
    0.15
     respectively
    0.12
    depending
    0.12
     thereof
    0.11
     if
    0.10
     etc
    0.10
     Arist
    0.10
    utas
    0.09
     alike
    0.09
     tamp
    0.09
    Activations Density 0.262%

    No Known Activations