© 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. 106592
    Prev
    Next
    INDEX
    Explanations

    actions related to sports plays and movements

    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
    quette
    -0.09
    jspx
    -0.09
     *,↵
    -0.08
    алов
    -0.08
    .setViewport
    -0.08
    íĸ
    -0.08
     temin
    -0.08
    .scalablytyped
    -0.08
    .Safe
    -0.08
    ãĥĵãĥ¼
    -0.08
    POSITIVE LOGITS
     everyone
    0.06
    ...↵
    0.06
    ↵
    0.06
     national
    0.06
    323
    0.06
     everybody
    0.06
     competition
    0.06
     shit
    0.06
     ...↵
    0.05
    È
    0.05
    Activations Density 0.007%

    No Known Activations