© 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. 125061
    Prev
    Next
    INDEX
    Explanations

    numerical values, regulations, and orders within a formal context

    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
     Amp
    -0.07
     Municip
    -0.07
    AMP
    -0.07
     amp
    -0.06
    amp
    -0.06
    gré
    -0.06
    quit
    -0.06
     AMP
    -0.06
    arro
    -0.06
    arası
    -0.06
    POSITIVE LOGITS
    uci
    0.07
    GBK
    0.07
    Regs
    0.07
    -regexp
    0.07
    afa
    0.06
     Gazette
    0.06
    .LENGTH
    0.06
    STREAM
    0.06
    ottle
    0.06
    Stream
    0.06
    Activations Density 0.002%

    No Known Activations