© 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. 20228
    Prev
    Next
    INDEX
    Explanations

    days, years, months, moments

    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
     times
    -0.11
    æĹ¶ä»£
    -0.11
     period
    -0.10
    utr
    -0.10
     era
    -0.10
    _argv
    -0.09
     Era
    -0.09
    æĻĤ代
    -0.09
    usi
    -0.09
    aty
    -0.09
    POSITIVE LOGITS
     inaugural
    0.10
    iguiente
    0.10
     Trent
    0.09
    natal
    0.09
     Santo
    0.09
    luet
    0.09
     Rath
    0.09
     Baltic
    0.09
    ané
    0.09
    avigator
    0.09
    Activations Density 0.096%

    No Known Activations