© 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. 33808
    Prev
    Next
    INDEX
    Explanations

    surprise and related emotions

    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
    .scalablytyped
    -0.14
     fascinated
    -0.11
     bewild
    -0.09
    úsqueda
    -0.09
     Kah
    -0.09
    arkan
    -0.08
    Unchecked
    -0.08
    hou
    -0.08
    ëĿ¼ëıĦ
    -0.08
    à¸Ļาà¸Ļ
    -0.08
    POSITIVE LOGITS
     surprise
    0.63
     Surprise
    0.50
     surprised
    0.49
     Sur
    0.47
     surpr
    0.46
    Sur
    0.45
    sur
    0.45
     surprises
    0.45
    -sur
    0.43
     SUR
    0.40
    Activations Density 0.100%

    No Known Activations