© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33770
    Prev
    Next
    INDEX
    Explanations

    drawing geometric shapes

    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
    polygon
    -0.10
    pherical
    -0.09
     cylindrical
    -0.09
     debt
    -0.09
     accordion
    -0.09
     newer
    -0.09
    ayers
    -0.09
     slick
    -0.09
     glyphs
    -0.09
     fo
    -0.08
    POSITIVE LOGITS
     circle
    0.14
     Circle
    0.14
     filled
    0.13
     Koch
    0.13
    Filled
    0.12
     Mand
    0.12
    filled
    0.12
     red
    0.11
     equ
    0.11
     circles
    0.11
    Activations Density 0.142%

    No Known Activations