© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4495
    Prev
    Next
    INDEX
    Explanations

    topics related to foreign exchange markets and their regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patri
    -0.07
     Patron
    -0.06
    strup
    -0.06
     Wahl
    -0.06
    arde
    -0.06
     dele
    -0.06
     Tits
    -0.06
     patri
    -0.06
    roat
    -0.06
    ulan
    -0.06
    POSITIVE LOGITS
     Exchange
    0.09
     exchanges
    0.08
     exchange
    0.08
     traded
    0.08
     transactions
    0.08
    Exchange
    0.07
    æĴ®
    0.07
    exchange
    0.07
    markets
    0.07
     daily
    0.07
    Activations Density 0.020%

    No Known Activations