© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81634
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure elements, such as method calls and object creation patterns

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    lek
    -0.06
     intellig
    -0.06
     Cohen
    -0.06
    ail
    -0.05
    assi
    -0.05
    ik
    -0.05
    inder
    -0.05
    InInspector
    -0.05
     chart
    -0.05
     miniature
    -0.05
    POSITIVE LOGITS
    елÑİ
    0.08
    elerik
    0.08
    ÅĻed
    0.08
     ÄĮeská
    0.07
    ī
    0.07
    رج
    0.07
    .Matchers
    0.07
    ëĵł
    0.07
    ivi
    0.07
    MeasureSpec
    0.07
    Activations Density 0.023%

    No Known Activations