© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 76069
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, particularly islands and notable 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
     Chicago
    -0.07
    ib
    -0.07
    \grid
    -0.07
     chicago
    -0.07
    ض
    -0.07
    okol
    -0.07
    amiento
    -0.06
     Illinois
    -0.06
    Chicago
    -0.06
    zier
    -0.06
    POSITIVE LOGITS
     traditional
    0.06
    å¡
    0.06
    iyan
    0.06
    ávÄĽ
    0.06
    館
    0.06
    brace
    0.06
     shallow
    0.06
     traditionally
    0.06
    UK
    0.06
    combe
    0.06
    Activations Density 0.002%

    No Known Activations