© 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. 89186
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports statistics and player performance metrics

    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
    .openConnection
    -0.07
    ãĥĨãĥ«
    -0.07
    abar
    -0.07
    icism
    -0.07
    ABSPATH
    -0.07
    ifornia
    -0.07
    kah
    -0.07
    /../
    -0.07
    yat
    -0.07
    Ģ
    -0.07
    POSITIVE LOGITS
     another
    0.08
    icts
    0.07
     an
    0.07
    uce
    0.07
     some
    0.06
     two
    0.06
    wards
    0.06
    athers
    0.06
    oppins
    0.06
    inos
    0.06
    Activations Density 0.003%

    No Known Activations