© 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. 42547
    Prev
    Next
    INDEX
    Explanations

    references to sports events and related terminology

    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
    /Dk
    -0.07
    .MessageBox
    -0.07
     "\",
    -0.06
    ahun
    -0.06
     league
    -0.06
    олоÑĤ
    -0.06
     Protector
    -0.06
    enler
    -0.06
    indsight
    -0.06
     Qed
    -0.06
    POSITIVE LOGITS
     Team
    0.10
    Team
    0.09
    -team
    0.07
     TEAM
    0.07
     team
    0.07
     captains
    0.07
     Captain
    0.07
    team
    0.07
    .INSTANCE
    0.07
     captain
    0.07
    Activations Density 0.018%

    No Known Activations