© 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. 91759
    Prev
    Next
    INDEX
    Explanations

    references to "Pan" and its related contexts, likely indicating a focus on a specific subject or theme associated with the term

    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
    sz
    -0.07
    emente
    -0.07
    ázev
    -0.06
    _REAL
    -0.06
     Gaga
    -0.06
    enticator
    -0.06
    ainment
    -0.06
    THREAD
    -0.06
     Huffman
    -0.06
    ë°ķ
    -0.06
    POSITIVE LOGITS
     pan
    0.10
     Pan
    0.08
    asonic
    0.08
    theon
    0.08
    pan
    0.07
    eras
    0.07
    zer
    0.07
    Pan
    0.07
    bian
    0.07
    ther
    0.07
    Activations Density 0.011%

    No Known Activations