© 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 EvalsExportsinterp-engineNEWAPI 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. 54306
    Prev
    Next
    INDEX
    Explanations

    phrases indicating athletic performance and achievements

    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
    agma
    -0.07
    åľ°ä¸ĭ
    -0.07
     earthquake
    -0.07
     bottoms
    -0.07
    _anchor
    -0.07
    footer
    -0.07
     heavyweight
    -0.07
    æĬ¬
    -0.07
    bottom
    -0.07
    /footer
    -0.07
    POSITIVE LOGITS
     wing
    0.09
     wings
    0.08
     winger
    0.08
     Guitar
    0.07
    翼
    0.07
    wing
    0.07
     guitar
    0.07
     cánh
    0.07
     Wing
    0.07
     bird
    0.07
    Activations Density 0.151%

    No Known Activations