© 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. 74366
    Prev
    Next
    INDEX
    Explanations

    indicators of market volatility 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
    aldi
    -0.07
    aupt
    -0.07
    atrix
    -0.07
    abay
    -0.06
    cab
    -0.06
    eling
    -0.06
     dilig
    -0.06
    onda
    -0.06
    Ú¯ÛĮر
    -0.06
    ãĥģãĥ¥
    -0.06
    POSITIVE LOGITS
    inet
    0.07
    oron
    0.07
    inker
    0.07
    INET
    0.07
     Vulcan
    0.07
     resta
    0.06
     Mash
    0.06
     Bor
    0.06
    ÙĨج
    0.06
    ramework
    0.06
    Activations Density 0.002%

    No Known Activations