© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42708
    Prev
    Next
    INDEX
    Explanations

    financial data related to stock ownership and market shares

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    .scalablytyped
    -0.07
    ãĤıãģĽ
    -0.07
    enuity
    -0.07
    felt
    -0.06
     tent
    -0.06
     Unsigned
    -0.06
     guild
    -0.06
     defaultMessage
    -0.06
    Unsigned
    -0.06
     White
    -0.06
    POSITIVE LOGITS
     ownership
    0.07
     holdings
    0.07
     stocks
    0.07
     Cov
    0.07
     owning
    0.07
    /docs
    0.06
     shares
    0.06
    arrant
    0.06
    lesen
    0.06
     Alphabet
    0.06
    Activations Density 0.006%

    No Known Activations