© 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. 106589
    Prev
    Next
    INDEX
    Explanations

    references to challenges and difficult conditions in sports or competition

    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
    (describing
    -0.07
    antine
    -0.07
    ago
    -0.07
    ãĤ¿ãĥ¼
    -0.07
    ingleton
    -0.07
    sel
    -0.06
     onTouch
    -0.06
     wallpapers
    -0.06
     souÄįas
    -0.06
     Hud
    -0.06
    POSITIVE LOGITS
     rested
    0.08
     travel
    0.08
     Travel
    0.08
    travel
    0.07
    Travel
    0.06
     late
    0.06
     recently
    0.06
    feit
    0.06
    _travel
    0.06
     rains
    0.06
    Activations Density 0.042%

    No Known Activations