© 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. 63880
    Prev
    Next
    INDEX
    Explanations

    da or dau prefix

    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
    pro
    -0.16
    pi
    -0.12
    st
    -0.12
    la
    -0.11
    irt
    -0.11
    is
    -0.11
    ple
    -0.11
    ches
    -0.10
    v
    -0.10
    j
    -0.10
    POSITIVE LOGITS
     Nẵng
    0.19
    ftar
    0.16
     Vinci
    0.16
    ughters
    0.15
    VID
    0.15
    ughter
    0.14
    quir
    0.13
    oust
    0.13
    emons
    0.13
    (da
    0.12
    Activations Density 0.045%

    No Known Activations