© 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. 27393
    Prev
    Next
    INDEX
    Explanations

    references to code modules and libraries in programming contexts

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

    Code imports or module inclusion declarations, often with additional comment tokens or special syntax indicating programming-related elements like libraries, dependencies, or module imports.

    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
    edii
    -0.07
    .scalablytyped
    -0.07
    .djangoproject
    -0.07
    setattr
    -0.07
    illard
    -0.07
    alus
    -0.07
    Format
    -0.07
    iết
    -0.07
    ÑĤеÑĢн
    -0.07
    illo
    -0.07
    POSITIVE LOGITS
     imports
    0.13
     import
    0.12
     importing
    0.11
     Imports
    0.11
     imported
    0.11
    Imports
    0.10
    imports
    0.10
     Imported
    0.09
     Import
    0.09
    -import
    0.09
    Activations Density 0.129%

    No Known Activations