© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36351
    Prev
    Next
    INDEX
    Explanations

    'll need

    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
    -0.13
    大
    -0.12
    è¯Ŀ
    -0.10
    å°ı说
    -0.10
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.10
    å°ı
    -0.10
    人åijĺ
    -0.09
    ’;t
    -0.09
    /or
    -0.09
    venge
    -0.09
    POSITIVE LOGITS
    ÂĢÂ
    0.17
    ÂĿ
    0.14
    ÂĢÂĻ
    0.14
    /we
    0.13
    gether
    0.13
     been
    0.12
    outh
    0.11
    tempts
    0.11
    -eye
    0.10
    amp
    0.10
    Activations Density 0.186%

    No Known Activations