© 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. 117373
    Prev
    Next
    INDEX
    Explanations

    terms related to financial analysis and trading performance

    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
    å¼¥
    -0.08
    akov
    -0.07
    riz
    -0.07
    etes
    -0.07
    /Images
    -0.07
    iscard
    -0.07
    enko
    -0.07
    rý
    -0.07
    etter
    -0.07
    ẩm
    -0.07
    POSITIVE LOGITS
     various
    0.06
    /animate
    0.06
    grep
    0.06
     ph
    0.06
    i
    0.06
     fal
    0.06
    t
    0.06
     versus
    0.06
     breat
    0.06
     Ph
    0.06
    Activations Density 0.001%

    No Known Activations