© 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. 88604
    Prev
    Next
    INDEX
    Explanations

    geographical locations and regions

    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
    ocale
    -0.07
    ocket
    -0.07
     Hud
    -0.06
    conde
    -0.06
     “
    -0.06
    359
    -0.06
    istical
    -0.06
    ophage
    -0.06
     experimental
    -0.06
    icher
    -0.06
    POSITIVE LOGITS
    /misc
    0.08
    raquo
    0.07
    fuse
    0.07
    .Chain
    0.07
    åijĨ
    0.07
    vip
    0.07
     Morrow
    0.07
    lain
    0.06
    _sdk
    0.06
    EMALE
    0.06
    Activations Density 0.006%

    No Known Activations