© 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. 151
    Prev
    Next
    INDEX
    Explanations

    cross reactivity, enzyme immunoassay, number, junior

    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
    ï½±
    -0.08
    exampleInputEmail
    -0.07
    .googlecode
    -0.07
     zdrav
    -0.07
    @student
    -0.07
     Sheldon
    -0.07
    idUser
    -0.07
    .openapi
    -0.07
    adder
    -0.07
    ekil
    -0.06
    POSITIVE LOGITS
     müc
    0.09
     Ä°mpar
    0.09
     kaldır
    0.07
    /*č\n
    0.07
    SKU
    0.07
     ãħ¡
    0.07
     smr
    0.07
    ashi
    0.07
     kurtar
    0.07
     müda
    0.07
    Activations Density 3.037%

    No Known Activations