© 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. 14124
    Prev
    Next
    INDEX
    Explanations

    attributes and qualities related to emotional impact and artistic creativity

    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
     Kens
    -0.06
    erva
    -0.06
    loat
    -0.06
     Brunswick
    -0.06
     Vernon
    -0.05
    ationally
    -0.05
     bright
    -0.05
     Ruf
    -0.05
     Bea
    -0.05
     Century
    -0.05
    POSITIVE LOGITS
    екаÑĢ
    0.09
    atown
    0.07
    egree
    0.07
    hone
    0.07
    zing
    0.07
     aspect
    0.07
    igkeit
    0.07
     element
    0.07
    interop
    0.07
     feel
    0.07
    Activations Density 0.087%

    No Known Activations