© 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. 116464
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or emphasis

    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
    orra
    -0.08
    orrh
    -0.06
    éīĦ
    -0.06
    cho
    -0.06
    oglobin
    -0.06
    ť
    -0.06
    imer
    -0.06
    åĽ
    -0.06
    .nih
    -0.06
    Letter
    -0.06
    POSITIVE LOGITS
    OLON
    0.08
    sis
    0.07
    yy
    0.06
    ãģĹãģı
    0.06
    ä¸Ģ度
    0.06
    å¤ķ
    0.06
    ترÛĮÙĨ
    0.06
     же
    0.06
    uzey
    0.06
    scheduled
    0.06
    Activations Density 0.005%

    No Known Activations