© 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. 49376
    Prev
    Next
    INDEX
    Explanations

    guessing letter in word rules

    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
    -0.12
     Chess
    -0.11
     Guns
    -0.10
    Chess
    -0.10
    xde
    -0.10
    aln
    -0.09
    lj
    -0.09
     poker
    -0.09
    493
    -0.09
    .minecraft
    -0.09
    POSITIVE LOGITS
     guess
    0.29
     guesses
    0.24
     Guess
    0.23
     guessing
    0.23
    guess
    0.22
     guessed
    0.22
    Guess
    0.21
    çĮľ
    0.21
    (guess
    0.19
    _guess
    0.18
    Activations Density 0.076%

    No Known Activations