© 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. 4585
    Prev
    Next
    INDEX
    Explanations

    references to specific research models and coding systems in the context of scientific studies

    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
    loys
    -0.09
    cestor
    -0.07
    incident
    -0.07
    yms
    -0.07
    flashdata
    -0.07
    omer
    -0.07
    loth
    -0.07
    ocious
    -0.07
    innacle
    -0.07
    ungan
    -0.07
    POSITIVE LOGITS
    431
    0.07
    .Observable
    0.07
    651
    0.07
    /stream
    0.07
    andler
    0.07
     lunar
    0.06
     Hund
    0.06
     stream
    0.06
     Steele
    0.06
     fold
    0.06
    Activations Density 0.001%

    No Known Activations