© 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. 63299
    Prev
    Next
    INDEX
    Explanations

    references to colors and art materials

    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
    ogn
    -0.06
     mili
    -0.06
    /themes
    -0.06
    /source
    -0.06
     Woods
    -0.06
    ht
    -0.06
    lia
    -0.06
    /theme
    -0.06
    lod
    -0.05
     pul
    -0.05
    POSITIVE LOGITS
    _ros
    0.07
    -based
    0.07
    obus
    0.07
    ienne
    0.07
    izace
    0.07
    -paper
    0.07
    à¹Ħà¸Ĺย
    0.07
    ISTS
    0.07
    ists
    0.07
    -format
    0.07
    Activations Density 0.012%

    No Known Activations