© 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. 39706
    Prev
    Next
    INDEX
    Explanations

    fraud or not fraud classification

    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
     regardless
    -0.13
    .DataTable
    -0.09
    ults
    -0.09
    åijĪ
    -0.09
    imal
    -0.09
    illet
    -0.09
     statistic
    -0.09
     therefore
    -0.09
     up
    -0.08
     retro
    -0.08
    POSITIVE LOGITS
     segreg
    0.10
     kalk
    0.10
     bif
    0.09
     few
    0.09
    few
    0.09
    ugen
    0.09
    Intialized
    0.09
     wr
    0.08
     Eb
    0.08
     tête
    0.08
    Activations Density 0.459%

    No Known Activations