© 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. 51288
    Prev
    Next
    INDEX
    Explanations

    blindness and sight

    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
    okol
    -0.09
    abaj
    -0.09
     tez
    -0.08
    ibe
    -0.08
    baum
    -0.08
     Sokol
    -0.08
    ÑĨеÑĢ
    -0.08
    {:
    -0.08
     Reco
    -0.08
    464
    -0.08
    POSITIVE LOGITS
     blind
    0.43
     Blind
    0.40
    blind
    0.40
     blindness
    0.38
     sight
    0.37
    -blind
    0.35
     vision
    0.29
     Sight
    0.28
    çĽ
    0.26
     Vision
    0.24
    Activations Density 0.080%

    No Known Activations