© 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. 44717
    Prev
    Next
    INDEX
    Explanations

    cultural and artistic events

    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
    istor
    -0.11
     swear
    -0.09
     Articles
    -0.08
     ActiveSupport
    -0.08
     ethic
    -0.08
    unto
    -0.08
     personal
    -0.08
     business
    -0.08
    evin
    -0.08
     cadre
    -0.08
    POSITIVE LOGITS
     cultural
    0.45
     culture
    0.43
     Culture
    0.39
     Cultural
    0.37
    æĸĩåĮĸ
    0.35
    Culture
    0.34
     arts
    0.33
    culture
    0.32
     cultura
    0.30
    ultural
    0.29
    Activations Density 0.093%

    No Known Activations