© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    multiple meanings or possibilities

    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
    uyá»ĩt
    -0.09
    ibr
    -0.09
    ktop
    -0.09
    326
    -0.09
    ulty
    -0.08
    оÑģоб
    -0.08
    ibo
    -0.08
    uty
    -0.08
    805
    -0.08
    chal
    -0.08
    POSITIVE LOGITS
     different
    0.26
     things
    0.26
     possible
    0.20
    different
    0.18
    ä¸įåIJĮçļĦ
    0.18
     depending
    0.17
     possibilities
    0.17
    things
    0.16
     Things
    0.16
     ÑĢазнÑĭÑħ
    0.16
    Activations Density 0.088%

    No Known Activations