© 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. 104112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even"

    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
    pig
    -0.06
     coolest
    -0.06
     sane
    -0.06
     weakest
    -0.06
     Almost
    -0.06
    com
    -0.06
     longest
    -0.06
    faces
    -0.06
    nev
    -0.06
    te
    -0.05
    POSITIVE LOGITS
     more
    0.13
    more
    0.12
     MORE
    0.12
    -more
    0.11
    MORE
    0.10
    æĽ´å¤ļ
    0.10
     daha
    0.10
    _MORE
    0.10
     più
    0.10
    .more
    0.10
    Activations Density 0.008%

    No Known Activations