© 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. 32440
    Prev
    Next
    INDEX
    Explanations

    common ending words

    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
    872
    -0.10
     barr
    -0.10
     Gad
    -0.09
    ï¼ģ”;\n\n
    -0.09
     Stam
    -0.09
    maze
    -0.09
    ï¼Īç¬ij
    -0.08
    apper
    -0.08
    ç«¥
    -0.08
    elsius
    -0.08
    POSITIVE LOGITS
     OR
    0.12
     )\n\n\n\n\n\n\n\n
    0.09
    ëį°ìĿ´íĬ¸
    0.09
     Launcher
    0.08
    ORS
    0.08
    orgen
    0.08
    acha
    0.08
    OR
    0.08
     Floyd
    0.08
     SV
    0.08
    Activations Density 0.189%

    No Known Activations