© 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. 26763
    Prev
    Next
    INDEX
    Explanations

    actions related to a sports match, particularly those involving player movements and plays

    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
    uids
    -0.07
    isphere
    -0.07
    uder
    -0.07
    ests
    -0.07
    aro
    -0.07
    æ
    -0.06
    arra
    -0.06
    amik
    -0.06
    ascus
    -0.06
    arios
    -0.06
    POSITIVE LOGITS
     POD
    0.07
    unft
    0.06
    atial
    0.06
    idla
    0.06
     tá»
    0.06
     pass
    0.06
    oleÄį
    0.06
    Ing
    0.06
    ç·Ĵ
    0.06
    اÙĩÛĮ
    0.06
    Activations Density 0.031%

    No Known Activations