© 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. 63270
    Prev
    Next
    INDEX
    Explanations

    references to 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
    loys
    -0.07
    rsp
    -0.07
    angers
    -0.06
    寧
    -0.06
    iale
    -0.06
    InSection
    -0.06
    ials
    -0.06
    lessly
    -0.06
    agnar
    -0.06
    ût
    -0.06
    POSITIVE LOGITS
    456
    0.07
    ing
    0.07
    -themed
    0.07
    tainment
    0.07
    lah
    0.07
    190
    0.07
    525
    0.07
    eter
    0.07
    /language
    0.07
    eters
    0.06
    Activations Density 0.002%

    No Known Activations