© 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. 57758
    Prev
    Next
    INDEX
    Explanations

    phrases indicating observing or watching something outside a window

    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
    isure
    -0.07
    ÑĢой
    -0.07
    cai
    -0.07
    оÑĢаз
    -0.07
    cepts
    -0.07
    vet
    -0.06
    enberg
    -0.06
    934
    -0.06
    вок
    -0.06
    enn
    -0.06
    POSITIVE LOGITS
     window
    0.07
     toward
    0.07
    çªĹ
    0.07
    wards
    0.06
     prospects
    0.06
     prospect
    0.06
     spotting
    0.06
     Prospect
    0.06
     windows
    0.06
     towards
    0.06
    Activations Density 0.004%

    No Known Activations