© 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. 47111
    Prev
    Next
    INDEX
    Explanations

    Chinese, Korean, Vietnamese greetings

    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
     ç±
    -0.10
    DTD
    -0.09
    Ral
    -0.09
     ï½Į
    -0.09
     impres
    -0.09
    ãĤĮãģ©
    -0.09
    ongyang
    -0.09
    drs
    -0.09
    erialize
    -0.09
    Ñŀ
    -0.09
    POSITIVE LOGITS
    Hello
    0.10
     hello
    0.10
     Hello
    0.10
    otto
    0.10
    baugh
    0.10
    hello
    0.09
    hi
    0.09
     Mend
    0.09
     hi
    0.09
    lili
    0.09
    Activations Density 0.017%

    No Known Activations