© 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. 13408
    Prev
    Next
    INDEX
    Explanations

    XML tags like category, aim, cidade

    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
     Ot
    -0.11
     Sinclair
    -0.10
     Playground
    -0.10
    UrlParser
    -0.09
    dux
    -0.09
     Sou
    -0.09
    //{{
    -0.09
    apiro
    -0.09
    /umd
    -0.09
     comb
    -0.09
    POSITIVE LOGITS
     JAXBElement
    0.18
    !--
    0.14
    root
    0.13
     xml
    0.13
     xmlns
    0.13
     root
    0.12
    CDATA
    0.11
     XML
    0.11
    .xml
    0.11
     Root
    0.11
    Activations Density 0.037%

    No Known Activations