© 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. 26700
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive sports and performance

    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
    iona
    -0.07
    ampa
    -0.07
    odb
    -0.06
    agr
    -0.06
    alla
    -0.06
    uter
    -0.06
    htdocs
    -0.06
     cooper
    -0.06
    ensa
    -0.06
    ansen
    -0.06
    POSITIVE LOGITS
    RunWith
    0.07
    _again
    0.06
    bras
    0.06
    è½®
    0.06
    pone
    0.06
    ivable
    0.06
    pull
    0.06
    QRS
    0.06
    YL
    0.06
    ishlist
    0.06
    Activations Density 0.024%

    No Known Activations