© 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. 220
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and annotations, particularly those concerning code analysis and error handling

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

    Code annotations for static analysis that provide metadata to compilers and IDEs about code properties, typically related to null checking, code analysis, or special handling directives.

    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
    ede
    -0.07
     Bald
    -0.06
    agher
    -0.06
    pearance
    -0.06
    ystate
    -0.06
    gly
    -0.06
    933
    -0.06
     CLR
    -0.06
     lets
    -0.06
     Suarez
    -0.06
    POSITIVE LOGITS
    ablish
    0.07
    zelf
    0.07
     Kaiser
    0.07
    éĸ
    0.06
     Kimber
    0.06
     iParam
    0.06
    ahn
    0.06
    _exempt
    0.06
     Gaw
    0.06
     æģ
    0.06
    Activations Density 0.008%

    No Known Activations