© 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. 15-LLAMASCOPE-RES-131K
    11. 86068
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    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
     Farrell
    -0.06
    kovou
    -0.06
    [__
    -0.06
    ä¿Ŀéļľ
    -0.06
     chai
    -0.06
    aji
    -0.06
    iative
    -0.06
     Led
    -0.06
    apse
    -0.06
    itational
    -0.06
    POSITIVE LOGITS
     Syntax
    0.07
     TMPro
    0.06
    urum
    0.06
    ̧
    0.06
    arters
    0.06
    .std
    0.06
    ec
    0.06
    afi
    0.06
    dam
    0.06
    lescope
    0.06
    Activations Density 0.002%

    No Known Activations