© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84721
    Prev
    Next
    INDEX
    Explanations

    occurrences of the action verb "do"

    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
    hood
    -0.07
    ly
    -0.06
     Intr
    -0.06
    ros
    -0.06
    np
    -0.06
     Nag
    -0.06
    orado
    -0.05
    جÙĩ
    -0.05
    οÏĤ
    -0.05
    /down
    -0.05
    POSITIVE LOGITS
    ãģ«ãģĭ
    0.07
    ekce
    0.07
    eno
    0.07
    .UnitTesting
    0.07
    emailer
    0.07
    ìĿ¼ìĹIJ
    0.07
    nings
    0.07
    adir
    0.07
    OrUpdate
    0.07
    cket
    0.07
    Activations Density 0.024%

    No Known Activations