© 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. 4415
    Prev
    Next
    INDEX
    Explanations

    references to popular culture, specifically books and movies

    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
    .scalablytyped
    -0.08
    tridge
    -0.07
    ëĤ´ê¸°
    -0.07
     تسÙħ
    -0.07
    acute
    -0.07
     ì°©
    -0.06
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.06
    -forward
    -0.06
    ersiz
    -0.06
    _minor
    -0.06
    POSITIVE LOGITS
     beh
    0.06
     popular
    0.06
     Popular
    0.06
    ÑĪев
    0.06
    onu
    0.06
    Demand
    0.06
     è¾
    0.06
     coun
    0.06
    ennent
    0.06
     re
    0.06
    Activations Density 0.017%

    No Known Activations