© 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. 121410
    Prev
    Next
    INDEX
    Explanations

    references to self-reflective or questioning thoughts about 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
    oge
    -0.07
    gaard
    -0.07
    onder
    -0.07
    ood
    -0.07
    اج
    -0.07
     Sle
    -0.06
    å¼ĺ
    -0.06
    ZO
    -0.06
    ichi
    -0.06
    hd
    -0.06
    POSITIVE LOGITS
     others
    0.10
     other
    0.09
     elsewhere
    0.09
    uras
    0.08
    others
    0.07
     anderen
    0.06
    urat
    0.06
    istrovstvÃŃ
    0.06
     Others
    0.06
    åħ¶ä»ĸ
    0.06
    Activations Density 0.002%

    No Known Activations