© 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. 89507
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and game outcomes

    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
    obre
    -0.08
    abeth
    -0.07
    åĽ£
    -0.07
    [src
    -0.07
    entieth
    -0.07
    TriState
    -0.07
    996
    -0.07
    ilers
    -0.07
    eced
    -0.06
    ÃĹ↵↵
    -0.06
    POSITIVE LOGITS
    isor
    0.08
    bst
    0.06
    uve
    0.06
    uji
    0.06
    ano
    0.06
    gal
    0.06
     Hutch
    0.06
    isi
    0.06
    inder
    0.06
    urai
    0.06
    Activations Density 0.025%

    No Known Activations