© 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. 31676
    Prev
    Next
    INDEX
    Explanations

    references to new developments or innovations

    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
    quam
    -0.07
    .Networking
    -0.07
    .pivot
    -0.06
    foil
    -0.06
    们
    -0.06
     наÑĤ
    -0.06
     Cv
    -0.06
    人éĸĵ
    -0.06
    wat
    -0.06
     fame
    -0.06
    POSITIVE LOGITS
     MyBase
    0.07
    oyal
    0.07
     release
    0.06
    HeaderCode
    0.06
     unre
    0.06
     bosses
    0.06
    -release
    0.06
     new
    0.06
    ácil
    0.06
    adal
    0.06
    Activations Density 0.017%

    No Known Activations