© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61384
    Prev
    Next
    INDEX
    Explanations

    caught unprepared or in the act

    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
    arium
    -0.09
    EDIATE
    -0.09
    uit
    -0.09
    δά
    -0.09
     Dy
    -0.09
    ifen
    -0.09
     Bale
    -0.09
     Dame
    -0.08
    .executeQuery
    -0.08
     Hamp
    -0.08
    POSITIVE LOGITS
     caught
    0.16
     unaware
    0.16
     red
    0.15
    Caught
    0.15
    caught
    0.14
    red
    0.13
     Caught
    0.13
     act
    0.12
    -red
    0.11
     pants
    0.11
    Activations Density 0.025%

    No Known Activations