© 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. 89595
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
    опол
    -0.08
    ãģ®ãĤĤ
    -0.07
    .MixedReality
    -0.07
    StrictEqual
    -0.07
    dns
    -0.07
    SenderId
    -0.06
    .LayoutStyle
    -0.06
    /banner
    -0.06
     Econ
    -0.06
    PCI
    -0.06
    POSITIVE LOGITS
     rede
    0.07
    rott
    0.07
    ourg
    0.06
    okol
    0.06
     Ferry
    0.06
    ichert
    0.06
    perse
    0.06
    osu
    0.06
    ibold
    0.06
    robe
    0.06
    Activations Density 0.004%

    No Known Activations