© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 27697
    Prev
    Next
    INDEX
    Explanations

    see and watch

    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
     Sight
    -0.10
     remembered
    -0.09
    iero
    -0.09
     ãĥ¾
    -0.09
    407
    -0.08
    ï½°
    -0.08
     tit
    -0.08
     sensed
    -0.08
     amb
    -0.08
     intern
    -0.08
    POSITIVE LOGITS
     watch
    0.69
     watching
    0.62
     watched
    0.60
    watch
    0.58
     watches
    0.53
     Watch
    0.49
     WATCH
    0.46
    Watch
    0.45
    -watch
    0.43
    .watch
    0.42
    Activations Density 0.119%

    No Known Activations