© 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. 91532
    Prev
    Next
    INDEX
    Explanations

    programming constructs and code execution patterns

    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
    855
    -0.07
    icket
    -0.07
    rowad
    -0.06
    Å¡en
    -0.06
    ableView
    -0.06
    romosome
    -0.06
    TriState
    -0.06
     è±
    -0.06
    GenerationStrategy
    -0.06
    enc
    -0.06
    POSITIVE LOGITS
     Unity
    0.07
    inus
    0.06
    ãĥ
    0.06
     ìĽĶ
    0.06
    obby
    0.06
    _PUR
    0.06
     UNITY
    0.06
     nonatomic
    0.06
    Persistent
    0.06
    rive
    0.06
    Activations Density 0.175%

    No Known Activations