Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44805
    Prev
    Next
    INDEX
    Explanations

    different cultures often have different

    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
    /themes
    -0.09
     human
    -0.09
    inox
    -0.09
     bilingual
    -0.09
     Friendly
    -0.08
     friendly
    -0.08
     organic
    -0.08
    หม
    -0.08
    Friendly
    -0.08
    _bn
    -0.08
    POSITIVE LOGITS
     cultural
    0.29
    æĸĩåĮĸ
    0.26
     Cultural
    0.26
     culture
    0.25
     Culture
    0.24
    Culture
    0.20
     cultures
    0.20
    -cultural
    0.19
    ultural
    0.19
     문íĻĶ
    0.18
    Activations Density 0.070%

    No Known Activations