© 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. 63413
    Prev
    Next
    INDEX
    Explanations

    entity followed by possibility

    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
     æĺ¯
    -0.11
    éĥ½æĺ¯
    -0.11
    ï¼Įæĺ¯
    -0.10
     são
    -0.10
    çļĦæĺ¯
    -0.09
    <|begin_of_text|>
    -0.09
    ennent
    -0.09
    —;are
    -0.09
     adalah
    -0.09
     är
    -0.09
    POSITIVE LOGITS
     could
    0.29
     might
    0.24
     may
    0.20
     would
    0.19
    could
    0.17
     will
    0.16
     Could
    0.14
     pourrait
    0.14
     bisa
    0.14
     should
    0.13
    Activations Density 0.094%

    No Known Activations