© 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. 21820
    Prev
    Next
    INDEX
    Explanations

    efficient transactions or operations

    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
    _wallet
    -0.10
    .wallet
    -0.09
    inventory
    -0.09
    Invoice
    -0.09
    å¸ģ
    -0.09
    Wallet
    -0.09
    oothing
    -0.09
    ä¾¡æł¼
    -0.09
    ê°Ģ격
    -0.09
    139
    -0.08
    POSITIVE LOGITS
     transaction
    0.34
     transactions
    0.32
     transfer
    0.32
     transfers
    0.30
     Transfer
    0.26
    transfer
    0.25
    Transfer
    0.23
    transaction
    0.23
     Transaction
    0.23
     transf
    0.22
    Activations Density 0.119%

    No Known Activations