© 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. 23492
    Prev
    Next
    INDEX
    Explanations

    design and graphics

    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
     photographed
    -0.11
    isson
    -0.11
    trs
    -0.10
     pict
    -0.10
     Sculpt
    -0.09
     sculptures
    -0.09
    ottom
    -0.09
    Routing
    -0.09
    .JPG
    -0.09
     Flickr
    -0.09
    POSITIVE LOGITS
     graphics
    0.29
     graphic
    0.28
     design
    0.28
     Design
    0.23
    graphic
    0.23
     Graphics
    0.22
    design
    0.22
     art
    0.22
     гÑĢаÑĦ
    0.21
    graphics
    0.21
    Activations Density 0.162%

    No Known Activations