© 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. 49892
    Prev
    Next
    INDEX
    Explanations

    beaten egg or whisk together

    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
    unci
    -0.11
    cola
    -0.10
     bun
    -0.10
     Sax
    -0.10
    odyn
    -0.10
    ruc
    -0.10
     stakes
    -0.09
    aby
    -0.09
    bags
    -0.09
     Riv
    -0.09
    POSITIVE LOGITS
     egg
    0.29
    egg
    0.24
     Egg
    0.24
     beat
    0.22
     eggs
    0.22
     beaten
    0.20
     Ñıй
    0.19
    èĽĭ
    0.17
     beating
    0.17
     Beat
    0.17
    Activations Density 0.026%

    No Known Activations