© 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. 17-LLAMASCOPE-RES-131K
    11. 92583
    Prev
    Next
    INDEX
    Explanations

    topics related to sports, specifically basketball and lottery games

    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
     Alonso
    -0.06
     Radar
    -0.06
    ιά
    -0.06
     dele
    -0.06
    eba
    -0.06
    521
    -0.06
     invert
    -0.06
     "
    -0.06
     consum
    -0.05
    091
    -0.05
    POSITIVE LOGITS
    popular
    0.08
     popular
    0.08
     worldwide
    0.08
     popularity
    0.08
     Lesser
    0.08
    Sibling
    0.07
    enen
    0.07
     yearly
    0.07
     crow
    0.07
    enek
    0.07
    Activations Density 0.003%

    No Known Activations