© 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. 30820
    Prev
    Next
    INDEX
    Explanations

    references to consciousness and self-awareness

    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
    isle
    -0.08
    ÅĻ
    -0.08
    anzi
    -0.08
    ·
    -0.08
    axy
    -0.08
    taÅŁ
    -0.08
    justice
    -0.07
    ³
    -0.07
    aar
    -0.07
    ãģ¤ãģij
    -0.07
    POSITIVE LOGITS
    ness
    0.12
    (es
    0.09
    es
    0.09
    -aware
    0.08
     aware
    0.07
    fulness
    0.07
    iy
    0.07
    edly
    0.07
    pth
    0.06
    eldon
    0.06
    Activations Density 0.009%

    No Known Activations