© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60574
    Prev
    Next
    INDEX
    Explanations

    terms related to investment and finance

    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
    .scalablytyped
    -0.08
    еи
    -0.07
    tener
    -0.07
    нике
    -0.07
    fak
    -0.07
    CSR
    -0.07
    .Bunifu
    -0.07
    crast
    -0.07
    soever
    -0.07
     CSR
    -0.07
    POSITIVE LOGITS
     hedge
    0.09
     bets
    0.07
     bet
    0.07
     Soros
    0.07
    rove
    0.07
     strategies
    0.07
     macros
    0.07
     macro
    0.07
     fund
    0.07
     hed
    0.07
    Activations Density 0.006%

    No Known Activations