© 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. 17-LLAMASCOPE-RES-131K
    11. 93943
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports analysis and coaching

    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
    rippling
    -0.07
    unner
    -0.06
    mana
    -0.06
    ijo
    -0.06
    ased
    -0.06
    bare
    -0.06
    ullen
    -0.06
    /testing
    -0.06
    £i
    -0.06
     stakes
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    krv
    0.07
    ushman
    0.06
     improvement
    0.06
     hind
    0.06
     execution
    0.06
     Lesson
    0.06
    ë°ĺ
    0.06
    .Unity
    0.06
     improve
    0.06
    Activations Density 0.015%

    No Known Activations