© 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. 121627
    Prev
    Next
    INDEX
    Explanations

    specific colors and materials in a design or crafting context

    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
    -placeholder
    -0.08
    ListOf
    -0.07
    HITE
    -0.07
    GameManager
    -0.07
    evin
    -0.07
     mastur
    -0.07
    .edu
    -0.06
     addCriterion
    -0.06
    ArrayOf
    -0.06
    imb
    -0.06
    POSITIVE LOGITS
     Pok
    0.06
    TM
    0.06
    igkeit
    0.06
     Ori
    0.06
     Gree
    0.06
    âĦ¢
    0.06
     strain
    0.05
    aterangepicker
    0.05
    arity
    0.05
    ington
    0.05
    Activations Density 0.035%

    No Known Activations