© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89779
    Prev
    Next
    INDEX
    Explanations

    references to sports team rosters and player selections

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    idla
    -0.08
    ilim
    -0.07
    _redirected
    -0.07
    å¼ĺ
    -0.07
     dẫn
    -0.07
    áty
    -0.07
    ÑĢÑĥÑĩ
    -0.07
     견
    -0.07
    auge
    -0.07
    asurer
    -0.07
    POSITIVE LOGITS
     final
    0.08
    ãģĺãĤĥ
    0.07
    325
    0.06
     excess
    0.06
     overflow
    0.06
    final
    0.06
     selection
    0.06
     runtime
    0.06
    rim
    0.06
     assets
    0.06
    Activations Density 0.002%

    No Known Activations