© 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. 12585
    Prev
    Next
    INDEX
    Explanations

    magyar

    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
     pár
    -0.13
     vidé
    -0.13
     zev
    -0.12
     kä
    -0.12
     nÃŃ
    -0.11
     konkrét
    -0.11
     y
    -0.11
     rám
    -0.11
     ún
    -0.11
    lÃŃb
    -0.11
    POSITIVE LOGITS
     sz
    0.14
    gy
    0.14
     ny
    0.13
     mag
    0.13
    sz
    0.12
     gy
    0.12
     Ny
    0.12
     Sz
    0.12
     egy
    0.12
    ered
    0.12
    Activations Density 0.031%

    No Known Activations