© 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. 17-LLAMASCOPE-RES-131K
    11. 4130
    Prev
    Next
    INDEX
    Explanations

    references to academic papers, data sets, or scientific citations

    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
    aran
    -0.06
     lint
    -0.06
    Volumes
    -0.06
    udget
    -0.06
    ections
    -0.06
    ngrx
    -0.06
    à¸ļà¸ļ
    -0.06
     hans
    -0.06
    emens
    -0.05
     kor
    -0.05
    POSITIVE LOGITS
     table
    0.07
     Table
    0.07
    .getTable
    0.07
     columns
    0.07
    Table
    0.07
    <thead
    0.07
    rows
    0.07
     tab
    0.07
     piv
    0.06
    .tab
    0.06
    Activations Density 0.067%

    No Known Activations