© 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. 61009
    Prev
    Next
    INDEX
    Explanations

    references to tennis events and tournaments

    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
    ogue
    -0.06
     chain
    -0.06
    éĸ
    -0.05
    ÄŁ
    -0.05
     Inspector
    -0.05
     forge
    -0.05
    arks
    -0.05
     iTunes
    -0.05
    —to
    -0.05
     ç¯
    -0.05
    POSITIVE LOGITS
    ounce
    0.07
     æĻ´
    0.07
     defaultCenter
    0.07
    bounce
    0.07
    entai
    0.07
    _MEDIUM
    0.07
    flen
    0.07
    anki
    0.07
    tracts
    0.07
    _restrict
    0.07
    Activations Density 0.003%

    No Known Activations