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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17661
    Prev
    Next
    INDEX
    Explanations

    references to sports facilities and fields

    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
     bedside
    -0.06
    shan
    -0.06
    guided
    -0.06
    ouz
    -0.06
    cha
    -0.06
    aku
    -0.06
     tapered
    -0.06
    ãĥªãĥ³
    -0.06
    лÑı
    -0.06
    ÙģØ´
    -0.06
    POSITIVE LOGITS
     facility
    0.09
     field
    0.08
     facilities
    0.08
     grass
    0.08
     pitches
    0.07
     Facilities
    0.07
    -field
    0.07
     pitch
    0.07
     Facility
    0.07
     Field
    0.07
    Activations Density 0.006%

    No Known Activations