© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44512
    Prev
    Next
    INDEX
    Explanations

    interest rate

    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
     worth
    -0.09
    ãĢĢï¾ī
    -0.09
    éric
    -0.09
    hani
    -0.09
    ower
    -0.09
    ë¶Ī
    -0.09
    .ud
    -0.09
    Ratio
    -0.09
     amo
    -0.09
     depreci
    -0.08
    POSITIVE LOGITS
     rate
    0.27
     rates
    0.25
     Rate
    0.24
     interest
    0.24
     RATE
    0.22
     Rates
    0.22
     Interest
    0.21
    Interest
    0.20
    rate
    0.20
    .rate
    0.20
    Activations Density 0.053%

    No Known Activations