© 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. 58466
    Prev
    Next
    INDEX
    Explanations

    references to executives and their roles within companies

    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
    alach
    -0.08
    urum
    -0.07
    .googlecode
    -0.07
    venir
    -0.07
    astes
    -0.07
    irma
    -0.07
     Agencies
    -0.06
    orners
    -0.06
    abaj
    -0.06
    arend
    -0.06
    POSITIVE LOGITS
     sales
    0.07
     global
    0.06
     Americas
    0.06
     Sales
    0.06
    .ep
    0.06
     regional
    0.06
    Sales
    0.06
     head
    0.06
     division
    0.06
     chief
    0.06
    Activations Density 0.034%

    No Known Activations