© 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. 17-LLAMASCOPE-RES-131K
    11. 59955
    Prev
    Next
    INDEX
    Explanations

    instances of coaches and their related actions or roles in sports contexts

    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
     виконав
    -0.08
    opak
    -0.07
    /testify
    -0.07
    ANTE
    -0.07
    PropTypes
    -0.07
    celik
    -0.07
    ngrx
    -0.07
    енз
    -0.07
    ÚĺÙĨ
    -0.07
    ศ
    -0.07
    POSITIVE LOGITS
     coach
    0.12
     coaching
    0.10
     coaches
    0.10
     Coach
    0.10
     Coaching
    0.09
    Coach
    0.09
    coach
    0.08
     ê°IJëıħ
    0.07
     coached
    0.07
    çĽ£çĿ£
    0.07
    Activations Density 0.057%

    No Known Activations