© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    terms related to data storage and user tracking mechanisms on websites

    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
    loon
    -0.08
     vlas
    -0.07
    ä¿
    -0.07
    ovol
    -0.07
    æħ¢
    -0.07
    ettle
    -0.06
    uisse
    -0.06
    yte
    -0.06
    Å¡la
    -0.06
    ÑĦи
    -0.06
    POSITIVE LOGITS
     session
    0.08
     temporary
    0.07
    olders
    0.07
    /session
    0.07
     Session
    0.07
    -session
    0.07
     during
    0.06
    Transient
    0.06
     transient
    0.06
    session
    0.06
    Activations Density 0.002%

    No Known Activations