© 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. 18671
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and company 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
    -0.09
    ầm
    -0.08
    imson
    -0.07
    áct
    -0.07
    oid
    -0.07
    ī´
    -0.07
    leaflet
    -0.07
     âĹĦ
    -0.07
    ersed
    -0.07
    hec
    -0.07
    POSITIVE LOGITS
    /views
    0.05
    H
    0.05
    fol
    0.05
     Cand
    0.05
    gh
    0.05
    uy
    0.05
    еÑĢи
    0.05
    /../
    0.05
     fol
    0.05
    gli
    0.05
    Activations Density 0.000%

    No Known Activations