© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121623
    Prev
    Next
    INDEX
    Explanations

    points of interest related to film production and notable locations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    нав
    -0.08
     örgüt
    -0.07
    iae
    -0.07
    webtoken
    -0.07
    اÙĩر
    -0.07
    utton
    -0.07
    иÑģлов
    -0.07
    ylland
    -0.07
    utilus
    -0.07
    ÃĸL
    -0.07
    POSITIVE LOGITS
     location
    0.08
     locations
    0.08
     shot
    0.08
     production
    0.07
    fil
    0.07
     shoot
    0.07
     local
    0.07
     Locations
    0.07
     filming
    0.07
    shot
    0.07
    Activations Density 0.013%

    No Known Activations