© 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. 123268
    Prev
    Next
    INDEX
    Explanations

    key statistical terms and events in sports contexts, particularly cricket

    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
    rnek
    -0.06
     Mer
    -0.06
    avana
    -0.06
    amel
    -0.06
    éĵģ
    -0.06
    ردÙĩ
    -0.06
    iron
    -0.06
     iron
    -0.06
    rio
    -0.06
    ruk
    -0.06
    POSITIVE LOGITS
    низ
    0.07
    _recovery
    0.07
    estr
    0.06
    onse
    0.06
    \Foundation
    0.06
    TagName
    0.06
    PERT
    0.06
    WARN
    0.06
     Sommer
    0.06
    алÑĭ
    0.06
    Activations Density 0.007%

    No Known Activations