© 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. 104455
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Julie" and its variations in the text

    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
    nis
    -0.08
    ekil
    -0.07
    itra
    -0.07
    è£ı
    -0.07
    OOM
    -0.07
    aliz
    -0.07
    esel
    -0.07
    ESC
    -0.07
    ria
    -0.07
    IMP
    -0.07
    POSITIVE LOGITS
    iswa
    0.07
    au
    0.07
    ±
    0.06
    quot
    0.06
    arrant
    0.06
    ystack
    0.06
    ellen
    0.06
    agues
    0.06
    cular
    0.06
    bracht
    0.06
    Activations Density 0.002%

    No Known Activations