© 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. 5-LLAMASCOPE-RES-131K
    11. 125703
    Prev
    Next
    INDEX
    Explanations

    references to leadership positions and organizational roles

    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
    ILER
    -0.06
    oya
    -0.06
    osy
    -0.06
    EMA
    -0.06
    84
    -0.06
    /mit
    -0.06
    el
    -0.06
    ADDR
    -0.06
    UFF
    -0.06
    ilers
    -0.06
    POSITIVE LOGITS
    ontent
    0.07
    .GroupLayout
    0.07
     faults
    0.07
    emme
    0.07
    ukan
    0.07
    ursal
    0.07
    blo
    0.07
    atables
    0.06
    atak
    0.06
    bru
    0.06
    Activations Density 0.050%

    No Known Activations