© 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. 61294
    Prev
    Next
    INDEX
    Explanations

    determine whether text has property

    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
    ÂĢÂĢ
    -0.12
    Âģ@
    -0.11
    ¶Į
    -0.10
    ¿ÃĤ
    -0.09
    -------------</
    -0.09
    ¦æĥħ
    -0.09
    atel
    -0.09
    ãģĵãĤį
    -0.09
    ©©
    -0.09
    ustos
    -0.09
    POSITIVE LOGITS
     contains
    0.13
     contain
    0.13
     is
    0.11
    contain
    0.11
     belong
    0.10
     ÑģодеÑĢж
    0.10
     ever
    0.09
    符åIJĪ
    0.09
     chứa
    0.09
     correctly
    0.09
    Activations Density 0.306%

    No Known Activations