© 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. 24371
    Prev
    Next
    INDEX
    Explanations

    triangular arbitrage

    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
    ungal
    -0.09
     Laden
    -0.08
     GHC
    -0.08
     rout
    -0.08
    _Framework
    -0.08
     pev
    -0.08
    AxisAlignment
    -0.08
     deeply
    -0.08
     GA
    -0.08
    uish
    -0.08
    POSITIVE LOGITS
     tzv
    0.16
     Reverse
    0.11
     ::::::::
    0.09
    imbus
    0.09
    ̧
    0.09
    ublik
    0.08
     ResourceType
    0.08
     reverse
    0.08
    arez
    0.08
     («
    0.08
    Activations Density 0.251%

    No Known Activations