© 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. 22903
    Prev
    Next
    INDEX
    Explanations

    detecting negation

    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
    IgnoreCase
    -0.10
    olla
    -0.09
     ниÑĩего
    -0.09
     ниÑĩ
    -0.09
    ingen
    -0.09
    Never
    -0.09
     NEVER
    -0.09
     -âĢIJ
    -0.08
     Never
    -0.08
     никогда
    -0.08
    POSITIVE LOGITS
     not
    0.43
    not
    0.28
     не
    0.26
     Not
    0.25
     không
    0.24
    Not
    0.24
    ä¸įæĺ¯
    0.23
     nicht
    0.22
     NOT
    0.22
    并ä¸į
    0.21
    Activations Density 0.143%

    No Known Activations