© 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. 51116
    Prev
    Next
    INDEX
    Explanations

    canvas context JavaScript

    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
     unt
    -0.10
    curl
    -0.10
     pun
    -0.09
     yOffset
    -0.09
     pans
    -0.09
     Wig
    -0.09
     xOffset
    -0.09
    ł
    -0.09
    WindowText
    -0.08
     screenSize
    -0.08
    POSITIVE LOGITS
     canvas
    0.28
     Canvas
    0.24
     ctx
    0.22
    canvas
    0.21
    Canvas
    0.19
     canv
    0.19
    .canvas
    0.18
    ctx
    0.18
    (ctx
    0.17
    (canvas
    0.17
    Activations Density 0.036%

    No Known Activations