© 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. 18706
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to software development and programming

    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
    ingle
    -0.07
    aka
    -0.07
    de
    -0.06
     anything
    -0.06
    lyn
    -0.06
    448
    -0.06
    getDefault
    -0.06
    aston
    -0.06
    279
    -0.05
     majority
    -0.05
    POSITIVE LOGITS
     meiner
    0.07
    ameleon
    0.07
    ãģ¬
    0.07
    _cpp
    0.07
    ÑĢиÑĦ
    0.07
    ÑĨеÑĢ
    0.06
    (non
    0.06
    .managed
    0.06
    roupon
    0.06
    Guy
    0.06
    Activations Density 0.025%

    No Known Activations