© 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. 38266
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and software development concepts, particularly in iOS development

    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
    DEM
    -0.07
    ONTAL
    -0.07
    VK
    -0.07
    ilir
    -0.07
     PANEL
    -0.06
    .VideoCapture
    -0.06
    APON
    -0.06
    VD
    -0.06
     OkHttpClient
    -0.06
    Camb
    -0.06
    POSITIVE LOGITS
    orage
    0.07
     Maver
    0.06
    _bd
    0.06
     Bud
    0.06
     ORM
    0.06
     prolific
    0.06
     patriarch
    0.06
     Brid
    0.06
     Arch
    0.06
     field
    0.06
    Activations Density 0.000%

    No Known Activations