© 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. 32301
    Prev
    Next
    INDEX
    Explanations

    game elements and stats

    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
    æ£ĭ
    -0.10
     Reeves
    -0.10
    /games
    -0.10
    ©©
    -0.10
    mamak
    -0.09
     Gameplay
    -0.09
    azole
    -0.09
     Counts
    -0.09
    _Anim
    -0.09
     playable
    -0.09
    POSITIVE LOGITS
     battle
    0.16
     fight
    0.16
     HP
    0.14
     monster
    0.14
     health
    0.13
     quest
    0.13
     character
    0.13
    HP
    0.13
     boss
    0.13
     inventory
    0.13
    Activations Density 0.134%

    No Known Activations