© 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. 31682
    Prev
    Next
    INDEX
    Explanations

    references to table columns and their configurations in coding or data structures

    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
    àµįà´
    -0.07
    downloads
    -0.07
    lemen
    -0.07
    ëģĶ
    -0.07
    usable
    -0.07
    én
    -0.07
    ron
    -0.07
    ut
    -0.07
    abal
    -0.07
    icable
    -0.07
    POSITIVE LOGITS
    arity
    0.08
    aires
    0.08
    ãĤº
    0.08
    atura
    0.08
    ander
    0.08
    /column
    0.07
    aire
    0.07
    -length
    0.07
    ar
    0.06
    _priv
    0.06
    Activations Density 0.022%

    No Known Activations