© 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. 69460
    Prev
    Next
    INDEX
    Explanations

    the name "Lee" and its variants appearing in various contexts

    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
    st
    -0.09
    mente
    -0.08
    IMS
    -0.07
    ãģĬãĤĬ
    -0.07
    dür
    -0.07
    ness
    -0.07
    gle
    -0.07
    kova
    -0.06
    war
    -0.06
    ichier
    -0.06
    POSITIVE LOGITS
    pered
    0.07
    bron
    0.07
    chw
    0.07
    Roy
    0.07
    eee
    0.07
    porter
    0.07
    uw
    0.07
    usercontent
    0.07
    kest
    0.07
    uraa
    0.07
    Activations Density 0.008%

    No Known Activations