© 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. 59678
    Prev
    Next
    INDEX
    Explanations

    sight and seeing

    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
    надлеж
    -0.11
    âĦĸâĦĸ
    -0.11
    ¶Į
    -0.11
    adu
    -0.10
    UMB
    -0.10
     Dah
    -0.10
    idor
    -0.09
    uch
    -0.09
     Graz
    -0.09
     недел
    -0.09
    POSITIVE LOGITS
    seeing
    0.29
     sight
    0.16
     gag
    0.15
     Sight
    0.15
    se
    0.14
    ight
    0.13
    geist
    0.13
    Seeing
    0.13
    ightly
    0.13
    ings
    0.12
    Activations Density 0.015%

    No Known Activations