© 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. 13813
    Prev
    Next
    INDEX
    Explanations

    European Union funding and money transfers

    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
     Monetary
    -0.11
    akh
    -0.10
     amor
    -0.09
     Nich
    -0.09
    ierge
    -0.09
     swing
    -0.09
    emet
    -0.08
    eward
    -0.08
    Wallet
    -0.08
     Shi
    -0.08
    POSITIVE LOGITS
     funds
    0.48
     Funds
    0.34
     fund
    0.34
     proceeds
    0.26
     mon
    0.24
     money
    0.24
     fond
    0.23
     Fund
    0.22
    èµĦéĩij
    0.21
     Proceed
    0.21
    Activations Density 0.087%

    No Known Activations