© 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. 121648
    Prev
    Next
    INDEX
    Explanations

    expressions of future potential and player development in sports contexts

    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
    tout
    -0.07
    .statistics
    -0.07
    Enlarge
    -0.07
     kriz
    -0.07
     geil
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    engin
    -0.07
    ilmington
    -0.07
    peÄį
    -0.07
    addtogroup
    -0.06
    POSITIVE LOGITS
     ours
    0.06
     our
    0.06
     nosso
    0.06
    -dismiss
    0.06
    ogue
    0.06
     Player
    0.06
    nero
    0.06
    ewis
    0.06
    urar
    0.06
     CVE
    0.05
    Activations Density 0.006%

    No Known Activations