© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 377
    Prev
    Next
    INDEX
    Explanations

    There are

    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
     tends
    -0.12
    shall
    -0.11
    inka
    -0.11
    estr
    -0.09
     shall
    -0.09
     Brad
    -0.09
    Bounding
    -0.09
     hadn
    -0.09
    ses
    -0.09
    538
    -0.09
    POSITIVE LOGITS
     are
    0.14
    for
    0.13
     jsou
    0.12
     sÄħ
    0.11
    after
    0.11
     sont
    0.11
     zijn
    0.11
    ewith
    0.10
    by
    0.10
     various
    0.10
    Activations Density 0.024%

    No Known Activations