© 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. 104272
    Prev
    Next
    INDEX
    Explanations

    terms related to stock performance and financial metrics

    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
    zcze
    -0.07
    urette
    -0.07
     either
    -0.07
    ubre
    -0.07
    umont
    -0.06
    élé
    -0.06
    zÃŃ
    -0.06
    okia
    -0.06
     Mood
    -0.06
    eru
    -0.06
    POSITIVE LOGITS
    isu
    0.07
     trend
    0.06
    à¹Ģย
    0.06
     Cotton
    0.06
    Ùģت
    0.06
    arking
    0.06
    adr
    0.06
    ترÙĦ
    0.06
     trends
    0.06
    /down
    0.06
    Activations Density 0.004%

    No Known Activations