© 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. 20243
    Prev
    Next
    INDEX
    Explanations

    playing games and making choices

    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
    jist
    -0.09
    anan
    -0.09
     Chess
    -0.08
    640
    -0.08
    å¼ĭ
    -0.08
     ADDR
    -0.08
    sehen
    -0.08
    ange
    -0.08
     Blick
    -0.08
     tük
    -0.08
    POSITIVE LOGITS
     secret
    0.16
     hints
    0.13
    secret
    0.12
     animal
    0.12
     guess
    0.12
     thinking
    0.12
    -secret
    0.12
     ÑģекÑĢеÑĤ
    0.12
     stump
    0.11
    ç§ĺ
    0.11
    Activations Density 0.221%

    No Known Activations