© 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. 25626
    Prev
    Next
    INDEX
    Explanations

    spectacular 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
     itk
    -0.09
    utilus
    -0.09
    lÃŃd
    -0.09
    огод
    -0.08
    printStats
    -0.08
    _vlog
    -0.08
    宿
    -0.08
     Fah
    -0.08
    IDEO
    -0.08
    uy
    -0.08
    POSITIVE LOGITS
     sight
    0.98
     Sight
    0.67
     sights
    0.63
     sighting
    0.40
     scene
    0.39
     spectacle
    0.37
     sightings
    0.33
    ight
    0.29
     seeing
    0.29
    scene
    0.28
    Activations Density 0.109%

    No Known Activations