© 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. 24392
    Prev
    Next
    INDEX
    Explanations

    Bengali and unusual characters

    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
    iddi
    -0.09
     имÑĥ
    -0.09
    oog
    -0.09
    ohana
    -0.09
    öyle
    -0.08
    ChangeEvent
    -0.08
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.08
     creampie
    -0.08
    ablish
    -0.08
     докÑĥм
    -0.08
    POSITIVE LOGITS
     Klo
    0.09
    997
    0.08
     Waters
    0.08
     sod
    0.08
     Paw
    0.08
    898
    0.08
    IMA
    0.08
     Extremely
    0.08
    0.08
    icle
    0.08
    Activations Density 0.235%

    No Known Activations