© 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. 63654
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by not

    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
     cant
    -0.13
    æ¬ł
    -0.11
     Horton
    -0.10
     Impossible
    -0.10
     Tess
    -0.09
    Impossible
    -0.09
     cres
    -0.09
    ARN
    -0.09
     Cant
    -0.09
     ÙħÙħÙĨ
    -0.09
    POSITIVE LOGITS
    ä¸įä¼ļ
    0.37
     doesn
    0.27
     didn
    0.25
     neither
    0.24
     won
    0.24
    won
    0.22
    并ä¸į
    0.21
     unlikely
    0.21
     tidak
    0.20
     does
    0.20
    Activations Density 0.125%

    No Known Activations