© 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. 51785
    Prev
    Next
    INDEX
    Explanations

    game, guess, chat, pretend

    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
     chess
    -0.13
     Chess
    -0.13
     Equality
    -0.10
    Chess
    -0.10
     equality
    -0.09
     crossword
    -0.09
     orthodox
    -0.09
    332
    -0.09
     fancy
    -0.09
     Tart
    -0.09
    POSITIVE LOGITS
     game
    0.19
     guessing
    0.17
     games
    0.14
     guess
    0.13
     rounds
    0.13
     Guess
    0.13
    ictionary
    0.13
    游æĪı
    0.12
    guess
    0.12
    game
    0.12
    Activations Density 0.122%

    No Known Activations