© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94654
    Prev
    Next
    INDEX
    Explanations

    references to sports venues and stadiums

    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
    weit
    -0.07
     Grain
    -0.06
     Plot
    -0.06
    634
    -0.06
    _GAIN
    -0.06
     grain
    -0.05
     Gain
    -0.05
     gain
    -0.05
    assis
    -0.05
    Gain
    -0.05
    POSITIVE LOGITS
    /kubernetes
    0.08
    нÑĸвеÑĢ
    0.07
     commission
    0.07
    quip
    0.07
    /goto
    0.07
    ลำ
    0.07
     лак
    0.07
    Ze
    0.07
    PILE
    0.07
    Commission
    0.07
    Activations Density 0.012%

    No Known Activations