© 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. 41692
    Prev
    Next
    INDEX
    Explanations

    references to sleep and related experiences

    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
    jte
    -0.07
    emann
    -0.06
    Locker
    -0.06
    جب
    -0.06
    ichel
    -0.06
    alternate
    -0.06
     serm
    -0.06
    upp
    -0.06
    moid
    -0.06
    hoa
    -0.06
    POSITIVE LOGITS
     sleep
    0.27
     Sleep
    0.23
    Sleep
    0.20
    sleep
    0.20
     sleeping
    0.20
     slept
    0.19
     sleeps
    0.18
    _sleep
    0.18
    çĿ¡
    0.17
     Sleeping
    0.17
    Activations Density 0.062%

    No Known Activations