© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21965
    Prev
    Next
    INDEX
    Explanations

    keen eye for vision

    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
    ãĥªãĤ¹
    -0.09
     svÄĽ
    -0.09
    бÑĢÑı
    -0.09
     Shelley
    -0.09
    uzey
    -0.09
    utm
    -0.09
     Thoughts
    -0.08
    idal
    -0.08
    unting
    -0.08
    ernote
    -0.08
    POSITIVE LOGITS
     vision
    0.52
     sight
    0.40
     Vision
    0.40
    vision
    0.35
    è§Ĩ
    0.35
     eyes
    0.34
    Vision
    0.33
     зÑĢениÑı
    0.33
     Sight
    0.31
    è¦ĸ
    0.29
    Activations Density 0.167%

    No Known Activations