© 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. 26472
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts in a codebase

    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
    (
    -0.06
    Synopsis
    -0.06
    ization
    -0.06
     Nó
    -0.06
     bins
    -0.06
    entials
    -0.06
    ore
    -0.06
    âĢ
    -0.06
     Platz
    -0.05
    lev
    -0.05
    POSITIVE LOGITS
    ewire
    0.08
    ména
    0.08
    <context
    0.08
    .localized
    0.07
    oÄŁ
    0.07
    \Bundle
    0.07
    ATAB
    0.07
    ">ÃĹ</
    0.07
    embre
    0.07
    EGIN
    0.07
    Activations Density 0.119%

    No Known Activations