© 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. 121620
    Prev
    Next
    INDEX
    Explanations

    structural elements and syntax in programming code

    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
    RIPT
    -0.08
    eniz
    -0.07
    regnum
    -0.07
    HideInInspector
    -0.07
    -caret
    -0.06
    FlowLayout
    -0.06
    reeze
    -0.06
     Isle
    -0.06
    _Framework
    -0.06
    PTION
    -0.06
    POSITIVE LOGITS
     let
    0.07
    chet
    0.06
    itches
    0.06
    ilate
    0.06
    entine
    0.06
    otos
    0.06
    urette
    0.05
    ubat
    0.05
     function
    0.05
    zing
    0.05
    Activations Density 0.016%

    No Known Activations