© 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. 24581
    Prev
    Next
    INDEX
    Explanations

    user interface design

    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
    _gui
    -0.11
    t
    -0.10
    d
    -0.10
    un
    -0.10
    lights
    -0.09
    TE
    -0.09
    ese
    -0.09
    993
    -0.09
    LD
    -0.09
    off
    -0.09
    POSITIVE LOGITS
     elements
    0.14
    /contentassist
    0.12
     Elements
    0.12
    Elements
    0.12
    (UI
    0.12
    WebView
    0.12
     components
    0.11
    ActionCreators
    0.11
    elements
    0.10
    _elements
    0.10
    Activations Density 0.044%

    No Known Activations