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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 33973
    Prev
    Next
    INDEX
    Explanations

    milk or milk variants

    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
    丸
    -0.11
     Chew
    -0.09
     Lem
    -0.09
     chemicals
    -0.09
     Buccane
    -0.09
     airflow
    -0.09
     Maver
    -0.09
     wines
    -0.09
    /Observable
    -0.09
    .compiler
    -0.09
    POSITIVE LOGITS
     milk
    0.38
     Milk
    0.31
     mil
    0.25
    ilk
    0.23
     sữa
    0.23
    ä¹³
    0.20
    奶
    0.20
     MIL
    0.18
     cream
    0.18
     dairy
    0.18
    Activations Density 0.058%

    No Known Activations