© 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. 33671
    Prev
    Next
    INDEX
    Explanations

    asking a question

    np_acts-logits-general · gemini-2.5-flash-lite

    common English function words, especially auxiliaries that start questions/requests and articles in noun phrases.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ï¿
    -0.09
     VÅ¡ech
    -0.08
     spe
    -0.08
     Catal
    -0.08
     Champagne
    -0.08
    Ìĥ
    -0.08
    ekim
    -0.08
     entr
    -0.08
    ÏĥÏĦÏĮ
    -0.08
     clo
    -0.07
    POSITIVE LOGITS
    866
    0.08
    èİİ
    0.08
    utut
    0.08
    æ´¥
    0.08
    {@
    0.08
    iker
    0.08
    amam
    0.08
    oldem
    0.08
    kB
    0.08
    _tokenize
    0.08
    Activations Density 0.448%

    No Known Activations