© 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. 9612
    Prev
    Next
    INDEX
    Explanations

    French contractions and possessives like c'est, d's

    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
    æŶåĢĻ
    -0.12
    ä¸Ģ级
    -0.11
    ’;t
    -0.11
    ’;nde
    -0.10
    人类
    -0.10
    Ùij
    -0.10
    å°ı说
    -0.10
    人åijĺ
    -0.10
    è¯Ŀ
    -0.10
    .Formatter
    -0.09
    POSITIVE LOGITS
    ÂĢÂĻ
    0.16
    ÂĢÂ
    0.16
    t
    0.13
    s
    0.12
    ropri
    0.12
    tempts
    0.12
    /'
    0.12
    ÂĿ
    0.11
    ll
    0.11
    p
    0.11
    Activations Density 0.217%

    No Known Activations