© 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. 89043
    Prev
    Next
    INDEX
    Explanations

    elements related to software development environments

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

    Directory paths and file structure references in software development contexts, particularly highlighting standard locations for resources, configurations, and code components.

    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
    oso
    -0.07
    åĬ
    -0.06
    alem
    -0.06
    burgh
    -0.06
    Ñıб
    -0.06
    acket
    -0.06
    eldom
    -0.06
    ogenic
    -0.06
    \Collections
    -0.06
    icol
    -0.06
    POSITIVE LOGITS
    /../
    0.08
    "+"
    0.07
    ávÄĽ
    0.07
    terior
    0.07
    esty
    0.07
    kami
    0.07
    ersed
    0.07
    lesen
    0.07
     há»ĵi
    0.06
    zier
    0.06
    Activations Density 0.014%

    No Known Activations