© 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. 55666
    Prev
    Next
    INDEX
    Explanations

    geographical references and names in the context of locations

    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
    Longrightarrow
    -0.06
    avanaugh
    -0.06
    æ·
    -0.06
    quit
    -0.06
     ÑģиÑĢ
    -0.06
     besie
    -0.06
     Nej
    -0.06
    ANY
    -0.06
     Cv
    -0.06
    emics
    -0.06
    POSITIVE LOGITS
     Border
    0.09
     border
    0.08
     Tibet
    0.08
    adow
    0.08
     Tibetan
    0.07
    -border
    0.07
    Border
    0.07
     mountain
    0.07
     Mountain
    0.07
     Himal
    0.07
    Activations Density 0.004%

    No Known Activations