© 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. 3531
    Prev
    Next
    INDEX
    Explanations

    key elements related to sports, specifically emphasizing performance and team statistics

    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
    adge
    -0.07
    hu
    -0.06
    erto
    -0.06
     map
    -0.06
     Coat
    -0.06
     bore
    -0.06
     Bearing
    -0.06
     Rt
    -0.05
    ere
    -0.05
    awn
    -0.05
    POSITIVE LOGITS
    /*č↵
    0.08
    uely
    0.07
    imedia
    0.07
    ASTE
    0.07
    .usermodel
    0.07
    ighbor
    0.07
    elig
    0.06
    æĤ
    0.06
    AXB
    0.06
    iface
    0.06
    Activations Density 0.002%

    No Known Activations