© 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. 121594
    Prev
    Next
    INDEX
    Explanations

    references to government, public-private partnerships, and employment statistics

    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
    linky
    -0.07
    erus
    -0.07
     Sands
    -0.07
    RTL
    -0.07
    yte
    -0.07
    émon
    -0.07
     ìĽ
    -0.07
    нике
    -0.06
    edia
    -0.06
    quette
    -0.06
    POSITIVE LOGITS
     Ur
    0.07
    047
    0.06
    .lucene
    0.06
    anie
    0.06
    CAST
    0.06
    adar
    0.06
     Transcript
    0.05
    -sidebar
    0.05
     thrust
    0.05
     suc
    0.05
    Activations Density 0.005%

    No Known Activations