© 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. 45370
    Prev
    Next
    INDEX
    Explanations

    evaluation of qualities

    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
     and
    -0.12
     or
    -0.09
     an
    -0.09
     nor
    -0.08
     plus
    -0.08
    人ãģ¯
    -0.08
     which
    -0.08
     that
    -0.08
     a
    -0.08
     anything
    -0.08
    POSITIVE LOGITS
    äºİ
    0.19
    æĸ¼
    0.17
     Ñīодо
    0.13
    对äºİ
    0.12
    à¹ĥà¸Ļà¸ģาร
    0.12
    èµ·æĿ¥
    0.10
     براÛĮ
    0.10
     благодаÑĢÑı
    0.10
     when
    0.09
    çļĦ人
    0.09
    Activations Density 0.582%

    No Known Activations