© 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. 2207
    Prev
    Next
    INDEX
    Explanations

    expressions related to awakening or becoming more conscious

    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
    anka
    -0.07
    .Throw
    -0.07
    imes
    -0.07
    ẩu
    -0.07
    تÙĤ
    -0.06
    lor
    -0.06
    opp
    -0.06
    .scalablytyped
    -0.06
     sway
    -0.06
    à¸Ńà¸Ľ
    -0.06
    POSITIVE LOGITS
     wake
    0.09
    Wake
    0.09
    éĨĴ
    0.09
     sleeping
    0.09
     Sleeping
    0.09
    /alert
    0.09
     Wake
    0.08
     sleeper
    0.08
    leep
    0.08
    Sleep
    0.08
    Activations Density 0.011%

    No Known Activations