© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88480
    Prev
    Next
    INDEX
    Explanations

    references to academic research and related roles in archaeology and anthropology

    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
    okers
    -0.07
    oker
    -0.07
     Sund
    -0.06
    rocket
    -0.06
    eton
    -0.06
    createdAt
    -0.06
    Rocket
    -0.06
    emand
    -0.06
     Curtain
    -0.06
    eroon
    -0.05
    POSITIVE LOGITS
     field
    0.09
    åįļçī©
    0.08
     museum
    0.08
     Sites
    0.07
    -field
    0.07
     Archae
    0.07
     tripod
    0.07
     Museum
    0.07
     Field
    0.07
    useum
    0.07
    Activations Density 0.039%

    No Known Activations