© 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. 9-LLAMASCOPE-RES-131K
    11. 99226
    Prev
    Next
    INDEX
    Explanations

    terms related to marathon running events

    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
    aliz
    -0.08
    ç³»
    -0.07
    iej
    -0.06
     reg
    -0.06
    edith
    -0.06
     div
    -0.06
    æľĭ
    -0.06
    iere
    -0.06
     occ
    -0.06
    tridge
    -0.06
    POSITIVE LOGITS
    oma
    0.07
    -long
    0.07
    ODULE
    0.07
    module
    0.07
     ausge
    0.06
     Arms
    0.06
    uga
    0.06
    ç«ľ
    0.06
     âĸ²
    0.06
    리
    0.06
    Activations Density 0.003%

    No Known Activations