© 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. 37594
    Prev
    Next
    INDEX
    Explanations

    I/you followed by an action

    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
     was
    -0.14
    ãģĹãģ¾ãģĹãģŁ
    -0.12
     داشت
    -0.12
    ноÑģи
    -0.12
     arose
    -0.11
    ëłĢ
    -0.11
     çıktı
    -0.10
    ãģ¾ãģĹãģŁ
    -0.10
     underwent
    -0.10
     yaptı
    -0.10
    POSITIVE LOGITS
     begin
    0.16
    ávajÃŃ
    0.16
     blir
    0.15
     becomes
    0.15
     are
    0.14
     become
    0.14
    аÑİÑĤ
    0.14
     decide
    0.13
     begins
    0.13
     aren
    0.13
    Activations Density 0.073%

    No Known Activations