© 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. 21985
    Prev
    Next
    INDEX
    Explanations

    billion and trillion figures

    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
    -million
    -0.13
     milion
    -0.13
     millionaire
    -0.12
     Million
    -0.12
    ä¸ĩåħĥ
    -0.12
    million
    -0.12
     Millions
    -0.11
     thous
    -0.11
    ä¸ĩåĨĨ
    -0.11
    ãĢĢãĤĿ
    -0.11
    POSITIVE LOGITS
     billions
    0.27
     billion
    0.27
    bill
    0.18
     milyar
    0.18
    bn
    0.17
    -billion
    0.17
     trillion
    0.17
     Bill
    0.16
     bl
    0.16
    Bill
    0.16
    Activations Density 0.053%

    No Known Activations