© 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. 55743
    Prev
    Next
    INDEX
    Explanations

    spending habits

    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
    profits
    -0.11
    ï¿£
    -0.10
    cmc
    -0.10
     Monetary
    -0.09
    ifu
    -0.09
    âĢIJâĢIJ
    -0.09
     Scha
    -0.09
     Farr
    -0.08
     unpaid
    -0.08
    jual
    -0.08
    POSITIVE LOGITS
     spending
    0.42
     spend
    0.38
     Spending
    0.30
     spends
    0.29
     Spend
    0.27
     spent
    0.26
     ÑĢаÑģÑħод
    0.24
     spender
    0.22
    èĬ±
    0.22
     spl
    0.21
    Activations Density 0.095%

    No Known Activations