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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89181
    Prev
    Next
    INDEX
    Explanations

    references to code and programming structures in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Programming code-related tokens and structures, particularly focusing on code generation, formatting, and syntax elements like namespaces, indentation, and function definitions in various programming languages (C#, PHP, JavaScript).

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ioned
    -0.06
    izons
    -0.06
    acco
    -0.06
    iyon
    -0.06
     curls
    -0.06
    erable
    -0.06
    burgh
    -0.06
     Corm
    -0.06
    vl
    -0.06
    ева
    -0.06
    POSITIVE LOGITS
     code
    0.07
    dash
    0.07
     outputFile
    0.06
     generated
    0.06
    /utility
    0.06
    ream
    0.06
    UPI
    0.06
    .opendaylight
    0.06
     Musik
    0.06
     Dash
    0.06
    Activations Density 0.020%

    No Known Activations