© 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. 60785
    Prev
    Next
    INDEX
    Explanations

    conducting a credit check

    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
     borrowing
    -0.17
     borrow
    -0.17
     borrowed
    -0.15
     creditor
    -0.11
     Borrow
    -0.10
     lender
    -0.10
    _receipt
    -0.10
    claimer
    -0.09
     Medicare
    -0.09
    orsi
    -0.09
    POSITIVE LOGITS
     credit
    0.28
    credit
    0.21
     Credit
    0.20
     risk
    0.20
    Credit
    0.18
     Risk
    0.16
     scoring
    0.14
    risk
    0.14
     default
    0.14
     Default
    0.14
    Activations Density 0.126%

    No Known Activations