© 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. 9-LLAMASCOPE-RES-131K
    11. 93981
    Prev
    Next
    INDEX
    Explanations

    programming language syntax, particularly related to loops and control 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
    aginator
    -0.09
    icana
    -0.09
    otate
    -0.09
    imas
    -0.09
    arih
    -0.08
    _chance
    -0.08
    omik
    -0.08
    arias
    -0.08
    wig
    -0.07
    Inlining
    -0.07
    POSITIVE LOGITS
     /↵
    0.06
    481
    0.06
     /
    0.06
    uits
    0.05
    588
    0.05
     analogy
    0.05
    432
    0.05
    تÙĨ
    0.05
     /\
    0.05
    968
    0.05
    Activations Density 0.010%

    No Known Activations