© 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. 120879
    Prev
    Next
    INDEX
    Explanations

    actions related to sports or physical activities

    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
    achel
    -0.06
    erre
    -0.06
    æĴ
    -0.06
     Klein
    -0.06
    roid
    -0.06
    mal
    -0.05
    semble
    -0.05
    ecure
    -0.05
    axis
    -0.05
    æº
    -0.05
    POSITIVE LOGITS
    IRE
    0.08
    erializer
    0.07
     Hollow
    0.07
    OLLOW
    0.07
    /LICENSE
    0.07
    itom
    0.06
    /react
    0.06
    ccione
    0.06
     arada
    0.06
    unted
    0.06
    Activations Density 0.002%

    No Known Activations