© 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. 77124
    Prev
    Next
    INDEX
    Explanations

    statistics and performance metrics related to sports teams

    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
    247
    -0.07
    ather
    -0.06
     reserve
    -0.06
    reserve
    -0.06
     Reserve
    -0.06
    reserved
    -0.06
    æ³ī
    -0.06
    ůl
    -0.05
    ắm
    -0.05
    acht
    -0.05
    POSITIVE LOGITS
    zier
    0.07
    ãĥ¼ãĥį
    0.07
     Strings
    0.07
    tplib
    0.07
     СеÑĢед
    0.06
     Kelley
    0.06
    öt
    0.06
    /apis
    0.06
    iser
    0.06
    IMIT
    0.06
    Activations Density 0.006%

    No Known Activations