© 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. 69221
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical references related to years or counts

    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
    enthal
    -0.06
    stood
    -0.06
    uos
    -0.06
    ird
    -0.06
    GAN
    -0.06
    feed
    -0.06
    ogne
    -0.06
    izens
    -0.06
    NL
    -0.06
    g
    -0.06
    POSITIVE LOGITS
     different
    0.09
    th
    0.08
    ä¸įåIJĮ
    0.08
     altogether
    0.07
    ìĽĶë¶ĢíĦ°
    0.07
    onda
    0.07
    nger
    0.07
    èĬĿ
    0.07
    .ImageAlign
    0.06
     (!
    0.06
    Activations Density 0.072%

    No Known Activations