© 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. 42771
    Prev
    Next
    INDEX
    Explanations

    financial debt and capital

    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
     Pis
    -0.10
    EDA
    -0.09
     unders
    -0.09
     profit
    -0.09
    culus
    -0.08
     доÑħод
    -0.08
     Roth
    -0.08
    acimiento
    -0.08
    lify
    -0.08
    usch
    -0.08
    POSITIVE LOGITS
     debt
    0.18
     senior
    0.16
     dele
    0.14
    è²ł
    0.14
     ratios
    0.14
     Debt
    0.14
     ratio
    0.13
     gearing
    0.13
    æĿ
    0.12
     funding
    0.12
    Activations Density 0.030%

    No Known Activations