© 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. 74584
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming-related language

    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
    apes
    -0.07
    nid
    -0.07
    onto
    -0.06
     Tampa
    -0.06
     Freder
    -0.06
    chaft
    -0.06
    aits
    -0.06
    à¤ľà¤¨
    -0.06
    nÃŃm
    -0.06
    apy
    -0.06
    POSITIVE LOGITS
    build
    0.07
    .ide
    0.07
    TREE
    0.07
    goog
    0.06
    UILD
    0.06
    ampo
    0.06
    onical
    0.06
    าะ
    0.06
    brook
    0.06
    RuleContext
    0.06
    Activations Density 0.013%

    No Known Activations