© 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. 76510
    Prev
    Next
    INDEX
    Explanations

    phrases indicating participation or involvement in significant sporting events or achievements

    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
    obra
    -0.09
    ulus
    -0.07
    911
    -0.07
    -transitional
    -0.07
    jsonp
    -0.07
    νοÏĤ
    -0.07
    ãĤ¦ãĥ³
    -0.07
    _TRANS
    -0.07
    portunity
    -0.06
    langs
    -0.06
    POSITIVE LOGITS
     history
    0.11
    adas
    0.08
    aph
    0.07
    history
    0.07
     History
    0.07
     ri
    0.07
     HISTORY
    0.07
    erver
    0.07
     histories
    0.06
    -history
    0.06
    Activations Density 0.010%

    No Known Activations