© 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. 15-LLAMASCOPE-RES-131K
    11. 26792
    Prev
    Next
    INDEX
    Explanations

    phrases indicating geographic locations or 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
    é¨
    -0.07
    agn
    -0.06
    ote
    -0.06
    oretical
    -0.06
     ej
    -0.06
     Hawkins
    -0.06
    reau
    -0.06
    stal
    -0.06
    миÑĢ
    -0.06
    ouv
    -0.06
    POSITIVE LOGITS
    .shtml
    0.07
    ancybox
    0.07
    orno
    0.07
    yles
    0.07
    sono
    0.07
    *pow
    0.06
    udev
    0.06
    .tm
    0.06
    asser
    0.06
    (core
    0.06
    Activations Density 0.006%

    No Known Activations