© 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. 26847
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and their associated context

    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
    ieten
    -0.06
     overhead
    -0.06
    <pre
    -0.06
    connexion
    -0.06
    jab
    -0.06
    icients
    -0.06
     вв
    -0.06
    /entities
    -0.05
    /platform
    -0.05
    chars
    -0.05
    POSITIVE LOGITS
    icher
    0.07
     ÎĶE
    0.07
    urdy
    0.07
    ripe
    0.07
     pair
    0.07
    -largest
    0.07
     piece
    0.07
    éĤ£ä¸ª
    0.07
    ancia
    0.07
    unsch
    0.07
    Activations Density 0.024%

    No Known Activations