© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 46025
    Prev
    Next
    INDEX
    Explanations

    обеспечение, баланс, код

    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
    Negative Logits
     звиÑĩай
    -0.15
     меÑģÑĤа
    -0.14
     имÑĥ
    -0.13
     елекÑĤÑĢон
    -0.13
    иÑĩеÑģÑĤво
    -0.13
    оÑģÑĤей
    -0.13
    еÑĩение
    -0.12
    ÙĮ
    -0.12
     заÑıв
    -0.12
     виÑıв
    -0.12
    POSITIVE LOGITS
    ении
    0.29
    лении
    0.26
    ÑģÑĤве
    0.25
    ании
    0.23
    身ä¸Ĭ
    0.21
    aniu
    0.21
     ÑĢоÑĨÑĸ
    0.17
     годÑĥ
    0.17
    алÑĮном
    0.17
    Ñģком
    0.16
    Activations Density 0.185%

    No Known Activations