© 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. 26985
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and syntax

    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
    viso
    -0.07
    ÑħÑĥ
    -0.07
    386
    -0.07
    ildren
    -0.07
    ÅĤu
    -0.07
     Nagar
    -0.06
    éł¼
    -0.06
    agar
    -0.06
    uru
    -0.06
    .IsNullOr
    -0.06
    POSITIVE LOGITS
    alsa
    0.07
    uesta
    0.06
     quad
    0.06
    affer
    0.06
     Sah
    0.06
    ãĥ³ãĥij
    0.06
    çĿ£
    0.06
     CONTRIBUTORS
    0.06
     ydk
    0.06
    ached
    0.06
    Activations Density 0.000%

    No Known Activations