© 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 EvalsExportsAPI 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. 93929
    Prev
    Next
    INDEX
    Explanations

    phrases related to task management or to-do lists

    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
    ly
    -0.08
    arily
    -0.07
    stro
    -0.07
    rt
    -0.06
    rim
    -0.06
    ud
    -0.06
    ru
    -0.06
    ÙĪراÙĨ
    -0.06
    gu
    -0.06
    ring
    -0.06
    POSITIVE LOGITS
    iele
    0.08
    isme
    0.07
    Å¡k
    0.07
    wner
    0.07
    alfa
    0.07
    inflate
    0.06
    oris
    0.06
    tolist
    0.06
    ledo
    0.06
    atron
    0.06
    Activations Density 0.003%

    No Known Activations