© 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. 18608
    Prev
    Next
    INDEX
    Explanations

    references to years, particularly in the early 2000s

    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
    coon
    -0.07
    ÑĮко
    -0.07
    ay
    -0.07
    285
    -0.07
     Jenner
    -0.07
    hetto
    -0.06
    oon
    -0.06
    do
    -0.06
    716
    -0.06
     Herrera
    -0.06
    POSITIVE LOGITS
    illisecond
    0.07
    ikel
    0.06
    ĩ
    0.06
    GTK
    0.06
     ArrayCollection
    0.06
    -aff
    0.06
    YPRE
    0.06
    riors
    0.06
    ths
    0.06
    isÃŃ
    0.06
    Activations Density 0.107%

    No Known Activations