© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21704
    Prev
    Next
    INDEX
    Explanations

    product view components

    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
     screenHeight
    -0.12
    -sidebar
    -0.12
    idebar
    -0.11
    -popup
    -0.10
    ķĮ
    -0.10
    sidebar
    -0.10
    çķĮ
    -0.10
    æ£ļ
    -0.09
    _popup
    -0.09
    Tooltip
    -0.09
    POSITIVE LOGITS
     Card
    0.13
     card
    0.13
     actions
    0.11
     links
    0.11
    Card
    0.11
     row
    0.11
     small
    0.11
     span
    0.11
     controls
    0.10
     secondary
    0.10
    Activations Density 0.130%

    No Known Activations