© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 103934
    Prev
    Next
    INDEX
    Explanations

    locations and activities related to outdoor recreation and tourism

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    InstanceOf
    -0.07
    entin
    -0.06
    azon
    -0.06
     lidi
    -0.06
    InSection
    -0.06
     bana
    -0.06
    ãĤ´ãĥª
    -0.06
    æ¡£
    -0.06
    ulan
    -0.06
    ãĥªãĥ³
    -0.06
    POSITIVE LOGITS
     cul
    0.06
    ød
    0.06
    ä¸Ńæĸĩ
    0.06
     withd
    0.06
     followed
    0.06
    WithDuration
    0.06
     Richardson
    0.06
    éd
    0.06
    quire
    0.06
     normally
    0.06
    Activations Density 0.025%

    No Known Activations