© 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. 89435
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating precision, efficiency, and systematic processes

    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
    ména
    -0.07
     PI
    -0.07
    999
    -0.07
    utex
    -0.06
    IDD
    -0.06
    930
    -0.06
    agina
    -0.06
    morgan
    -0.06
    iad
    -0.06
    æĬĬ
    -0.06
    POSITIVE LOGITS
    edBy
    0.07
     taken
    0.07
    plorer
    0.07
     lain
    0.06
    nil
    0.06
     Gand
    0.06
    vrier
    0.06
    ¤¤
    0.06
     ours
    0.06
     defe
    0.06
    Activations Density 0.042%

    No Known Activations