© 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. 80697
    Prev
    Next
    INDEX
    Explanations

    topics related to professional skills and creative expressions

    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
    este
    -0.07
    onet
    -0.07
    legate
    -0.06
    recent
    -0.06
    yet
    -0.06
    039
    -0.06
     recent
    -0.06
    æĽ¾
    -0.06
    alla
    -0.06
    agn
    -0.06
    POSITIVE LOGITS
    ubbo
    0.07
    bons
    0.07
     subt
    0.06
    Ctl
    0.06
    ushima
    0.06
    unfold
    0.06
    Cli
    0.06
    ubb
    0.06
    adians
    0.06
     sometimes
    0.06
    Activations Density 0.048%

    No Known Activations