© 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. 15-LLAMASCOPE-RES-131K
    11. 87067
    Prev
    Next
    INDEX
    Explanations

    references to specific regions, particularly Northern Ireland and Hong Kong

    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
    bidden
    -0.07
     trú
    -0.07
    allo
    -0.07
    ãĢħ
    -0.07
    baugh
    -0.07
    .Criteria
    -0.07
    LOCITY
    -0.07
     mekan
    -0.07
    _cast
    -0.07
    ka
    -0.07
    POSITIVE LOGITS
    ibble
    0.06
     اÙĦØ£ÙħرÙĬÙĥÙĬØ©
    0.06
    ollider
    0.06
    idget
    0.06
     Nim
    0.05
     Anders
    0.05
     Sawyer
    0.05
    ivot
    0.05
    Æ°á»Ľc
    0.05
     Hale
    0.05
    Activations Density 0.091%

    No Known Activations