© 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. 22383
    Prev
    Next
    INDEX
    Explanations

    non-standard encoding

    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
    actionDate
    -0.10
    ãĥ»ãĥ»ãĥ»\n\n
    -0.08
    ï¼¾
    -0.08
     âĢª
    -0.08
    bruar
    -0.07
    ãģŁãģ¡ãģ¯
    -0.07
    aginator
    -0.07
    JECTED
    -0.07
    NewProp
    -0.07
    Intialized
    -0.07
    POSITIVE LOGITS
     slight
    0.08
     оÑĢганиза
    0.07
    æĺ¯ä¸ª
    0.07
    .i
    0.07
    ail
    0.07
    æĺ¯ä¸Ģ个
    0.07
     possibly
    0.07
    (optional
    0.07
    buah
    0.07
     TBD
    0.07
    Activations Density 0.373%

    No Known Activations