© 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. 16176
    Prev
    Next
    INDEX
    Explanations

    interest you owe or is paid

    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
     deductible
    -0.09
     vend
    -0.09
     repay
    -0.09
     integerValue
    -0.08
     depreci
    -0.08
    asse
    -0.08
     å¯
    -0.08
     Vend
    -0.08
    ubi
    -0.08
    iped
    -0.08
    POSITIVE LOGITS
     interest
    0.32
     Interest
    0.29
    Interest
    0.27
    interest
    0.23
    _interest
    0.21
     interests
    0.20
    -interest
    0.18
     comp
    0.18
     compound
    0.18
     interesse
    0.17
    Activations Density 0.047%

    No Known Activations