© 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. 36074
    Prev
    Next
    INDEX
    Explanations

    usage and context

    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
     providing
    -0.10
    wg
    -0.09
    avia
    -0.09
     Dancing
    -0.09
    owler
    -0.09
    iming
    -0.08
    æĿ¥èĩª
    -0.08
    imits
    -0.08
    axter
    -0.08
     ï¾Ħ
    -0.08
    POSITIVE LOGITS
     surrounding
    0.18
     uses
    0.18
     associated
    0.17
     иÑģполÑĮз
    0.17
     containing
    0.16
     using
    0.16
     menggunakan
    0.16
    Containing
    0.15
     use
    0.15
    使çĶ¨
    0.15
    Activations Density 0.286%

    No Known Activations