© 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. 43745
    Prev
    Next
    INDEX
    Explanations

    as, in, a, prefixes

    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
    езд
    -0.12
    oretical
    -0.12
    xious
    -0.11
    olated
    -0.10
    leÅŁik
    -0.10
    ноÑģÑı
    -0.10
    ï¼ıï¼ıï¼ıï¼ıï¼ıï¼ıï¼ıï¼ı
    -0.10
    clusive
    -0.09
    acente
    -0.09
    неÑģÑĤи
    -0.09
    POSITIVE LOGITS
    elize
    0.17
    ifies
    0.16
    ify
    0.14
    izes
    0.14
    vertise
    0.14
    itize
    0.13
    ients
    0.13
    icip
    0.13
    imize
    0.12
    erialize
    0.12
    Activations Density 0.285%

    No Known Activations