© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29235
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to financial products and regulations

    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
     bidding
    -0.06
    894
    -0.06
     sát
    -0.06
    breadcrumbs
    -0.06
    _OM
    -0.06
     wages
    -0.06
     cade
    -0.06
    ker
    -0.06
    kul
    -0.06
     ฿
    -0.06
    POSITIVE LOGITS
     options
    0.09
     option
    0.08
     Options
    0.08
    /options
    0.08
     ann
    0.08
    options
    0.08
    WithOptions
    0.07
    Äįer
    0.07
    option
    0.07
    hiba
    0.07
    Activations Density 0.003%

    No Known Activations