© 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. 92988
    Prev
    Next
    INDEX
    Explanations

    references to sports events and athletes

    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
    ABCDEFG
    -0.07
    ëĶĶìĺ¤
    -0.07
     Gins
    -0.07
    žel
    -0.06
     Tops
    -0.06
     заг
    -0.06
    WindowState
    -0.06
    ebek
    -0.06
    ë·
    -0.06
    otle
    -0.06
    POSITIVE LOGITS
    aturated
    0.07
    htar
    0.07
    904
    0.06
     gold
    0.06
    738
    0.06
    eties
    0.06
     inline
    0.06
    516
    0.06
    ersion
    0.06
     silver
    0.06
    Activations Density 0.001%

    No Known Activations