© 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. 94673
    Prev
    Next
    INDEX
    Explanations

    phrases related to managing personal information and settings

    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
    isk
    -0.06
    amina
    -0.06
     hood
    -0.06
    fty
    -0.06
    ffen
    -0.06
    reater
    -0.06
     Moody
    -0.06
    -period
    -0.05
    imas
    -0.05
    aze
    -0.05
    POSITIVE LOGITS
     settings
    0.07
     tune
    0.07
     nguyá»ĩn
    0.07
     SETTINGS
    0.07
    preferences
    0.07
     preferences
    0.07
    settings
    0.07
    ãĥ¼ãĥĨ
    0.07
    /preferences
    0.07
    िथ
    0.07
    Activations Density 0.003%

    No Known Activations