© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89638
    Prev
    Next
    INDEX
    Explanations

    expressions of self-awareness and critical reflection on personal experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    conto
    -0.06
     Rou
    -0.06
     Kling
    -0.06
     Lad
    -0.06
    acyj
    -0.05
     prize
    -0.05
    Pager
    -0.05
     Gould
    -0.05
     chests
    -0.05
    ander
    -0.05
    POSITIVE LOGITS
     reviews
    0.09
     cazzo
    0.08
    .scalablytyped
    0.08
    ánh
    0.07
     Reviews
    0.07
    -review
    0.07
     review
    0.07
    ساÙĨÛĮ
    0.07
    _reviews
    0.07
    reviews
    0.07
    Activations Density 0.053%

    No Known Activations