© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35419
    Prev
    Next
    INDEX
    Explanations

    soy, bean, tofu

    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
    sto
    -0.10
    sth
    -0.10
    ulumi
    -0.10
    eyn
    -0.10
    sti
    -0.09
     Serena
    -0.09
    ordin
    -0.09
    incip
    -0.08
    adius
    -0.08
    èķī
    -0.08
    POSITIVE LOGITS
    bean
    0.27
    beans
    0.20
     sauce
    0.16
     bean
    0.16
     soy
    0.15
     Soy
    0.14
     Bean
    0.14
    inka
    0.14
     Iso
    0.13
    (bean
    0.13
    Activations Density 0.025%

    No Known Activations