© 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. 53807
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'export' in code or programming contexts

    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
     Cory
    -0.07
    bourne
    -0.07
     Candle
    -0.07
    .parameter
    -0.07
     pie
    -0.06
    .Parameter
    -0.06
    OrCreate
    -0.06
    chant
    -0.06
    mock
    -0.06
    нÑĸÑģÑĤ
    -0.06
    POSITIVE LOGITS
    yte
    0.08
     default
    0.08
    ed
    0.07
    yas
    0.07
    okus
    0.06
    ation
    0.06
     recip
    0.06
    edb
    0.06
    ίδ
    0.06
    ç¥
    0.06
    Activations Density 0.002%

    No Known Activations