© 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. 62320
    Prev
    Next
    INDEX
    Explanations

    financial metrics related to stock 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
    ContextHolder
    -0.07
     Federal
    -0.06
    unce
    -0.06
    ENTA
    -0.06
    ocode
    -0.06
    ÙĪÙĦØ©
    -0.06
    LEC
    -0.06
    readcr
    -0.06
    ichert
    -0.06
    .output
    -0.05
    POSITIVE LOGITS
    .opensource
    0.06
    itar
    0.06
    niÄį
    0.06
    ropolis
    0.06
     abdom
    0.06
    .Chain
    0.06
     kö
    0.06
     digest
    0.06
    chwitz
    0.06
    _digest
    0.06
    Activations Density 0.002%

    No Known Activations