© 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. 18833
    Prev
    Next
    INDEX
    Explanations

    references to science and technology agreements and collaborations

    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
    /embed
    -0.07
    ustainability
    -0.06
    engl
    -0.06
    mi
    -0.06
     graphene
    -0.06
    OffsetTable
    -0.06
    qli
    -0.06
    embed
    -0.06
     selfie
    -0.06
     shiny
    -0.06
    POSITIVE LOGITS
    198
    0.10
     USSR
    0.08
    197
    0.08
    199
    0.08
     Downs
    0.07
     Interracial
    0.07
     Consultants
    0.07
    ullan
    0.06
    YTE
    0.06
     Juda
    0.06
    Activations Density 0.221%

    No Known Activations