© 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. 104609
    Prev
    Next
    INDEX
    Explanations

    references to spatial organization and functionality within facilities

    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
     cover
    -0.07
    ibar
    -0.06
     covers
    -0.06
     coordinates
    -0.06
     eskort
    -0.06
    azon
    -0.06
    omi
    -0.06
    onga
    -0.06
    anus
    -0.06
    _barrier
    -0.06
    POSITIVE LOGITS
     Thief
    0.09
    ContentLoaded
    0.07
    è¼Ŀ
    0.07
     киÑĪ
    0.07
    ëŀĮ
    0.07
     Fans
    0.07
    .bunifuFlatButton
    0.07
     lou
    0.07
    zilla
    0.06
     اÙĦتص
    0.06
    Activations Density 0.004%

    No Known Activations