© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15619
    Prev
    Next
    INDEX
    Explanations

    references to the term "globe" and its variations in various contexts

    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
    HING
    -0.09
    agara
    -0.06
    yb
    -0.06
    rob
    -0.06
    awai
    -0.06
    oho
    -0.06
    ãģ£ãģ±ãģĦ
    -0.06
    aro
    -0.06
    pe
    -0.06
    oyal
    -0.06
    POSITIVE LOGITS
     trot
    0.08
     Trot
    0.08
     Booker
    0.07
    bedPane
    0.07
    bum
    0.07
    Viewer
    0.07
    bed
    0.07
    stance
    0.07
    .glob
    0.06
    ä»Ķ
    0.06
    Activations Density 0.003%

    No Known Activations