© 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. 88972
    Prev
    Next
    INDEX
    Explanations

    information related to sports events and their scheduling

    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
    æ¤į
    -0.07
     hann
    -0.07
    797
    -0.07
    .sdk
    -0.07
    stadt
    -0.06
    ura
    -0.06
    åĶ
    -0.06
    oli
    -0.06
    .tool
    -0.06
    Weekly
    -0.06
    POSITIVE LOGITS
     schedule
    0.07
    kate
    0.07
    MAND
    0.06
    ruc
    0.06
     Äĩe
    0.06
    央
    0.06
    IFO
    0.06
    _FP
    0.06
     dve
    0.06
    ãģ£ãģ¡
    0.06
    Activations Density 0.023%

    No Known Activations