© 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. 9-LLAMASCOPE-RES-131K
    11. 95231
    Prev
    Next
    INDEX
    Explanations

    references to leaders and their roles within organizations

    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
    .IContainer
    -0.08
    mada
    -0.07
    _ISR
    -0.07
    ạng
    -0.07
    esome
    -0.07
    ecut
    -0.07
    acier
    -0.07
    rella
    -0.07
    Ïģιν
    -0.07
    iland
    -0.06
    POSITIVE LOGITS
    ocos
    0.07
    agnost
    0.06
     roles
    0.06
    ictions
    0.06
    ships
    0.06
     Wid
    0.05
     deep
    0.05
     Anders
    0.05
    etler
    0.05
    heck
    0.05
    Activations Density 0.075%

    No Known Activations