© 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. 123466
    Prev
    Next
    INDEX
    Explanations

    content related to blog updates and follow-up posts

    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
    inia
    -0.07
     Pearson
    -0.07
    ýt
    -0.06
    978
    -0.06
    stable
    -0.06
    558
    -0.06
    orpion
    -0.06
    rzy
    -0.06
    tn
    -0.06
    úsqueda
    -0.06
    POSITIVE LOGITS
     blog
    0.20
     posts
    0.17
    blog
    0.17
    -blog
    0.16
    Blog
    0.16
     Blog
    0.15
     blogs
    0.15
     post
    0.14
     article
    0.14
    /blog
    0.14
    Activations Density 0.234%

    No Known Activations