© 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. 52206
    Prev
    Next
    INDEX
    Explanations

    specific weight and shape, pre-computed shadow maps

    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
    Ellipse
    -0.09
     GameController
    -0.09
    AffineTransform
    -0.09
     SQUARE
    -0.09
    QUARE
    -0.09
    CloseOperation
    -0.09
    polator
    -0.09
     ration
    -0.08
     Schmidt
    -0.08
    CGPoint
    -0.08
    POSITIVE LOGITS
     ray
    0.14
     World
    0.14
     world
    0.14
     mesh
    0.13
     frustr
    0.13
     volumes
    0.12
     nav
    0.12
     rag
    0.12
     AABB
    0.12
     WORLD
    0.12
    Activations Density 0.065%

    No Known Activations