© 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 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. 87944
    Prev
    Next
    INDEX
    Explanations

    references to competitive sports teams and their dynamics

    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
    aÄį
    -0.08
    orex
    -0.08
    olicit
    -0.07
    jang
    -0.07
    xt
    -0.07
    ileo
    -0.07
    ýt
    -0.07
    ijd
    -0.07
    757
    -0.07
    ambre
    -0.07
    POSITIVE LOGITS
     Objective
    0.08
     objective
    0.07
     Advantage
    0.07
     opposing
    0.07
    side
    0.06
     opposite
    0.06
     side
    0.06
     team
    0.06
     Popular
    0.06
     Coalition
    0.06
    Activations Density 0.012%

    No Known Activations