© 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. 62921
    Prev
    Next
    INDEX
    Explanations

    croissants and baked goods

    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
    ERM
    -0.09
     candies
    -0.09
     chocolates
    -0.09
    ATUS
    -0.09
    _soup
    -0.08
    clang
    -0.08
     Stra
    -0.08
    ￣￣
    -0.08
     bowls
    -0.08
    .tc
    -0.08
    POSITIVE LOGITS
     cro
    0.21
     dough
    0.19
     rolls
    0.19
     past
    0.18
     yeast
    0.17
     kne
    0.17
     pastry
    0.17
     puff
    0.17
     Cro
    0.15
     cres
    0.15
    Activations Density 0.053%

    No Known Activations