© 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. 9-LLAMASCOPE-RES-131K
    11. 95353
    Prev
    Next
    INDEX
    Explanations

    less-than symbols likely used in coding or programming contexts

    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
    790
    -0.07
    uke
    -0.06
    piel
    -0.06
    ç®±
    -0.06
    ĥ
    -0.06
     Schwar
    -0.06
    veloper
    -0.06
    Spi
    -0.06
    alian
    -0.06
    uki
    -0.06
    POSITIVE LOGITS
    igos
    0.07
    é¨
    0.07
    Macro
    0.07
    bourg
    0.07
    elerik
    0.07
    emoth
    0.07
    .ImageAlign
    0.07
    ırak
    0.07
    ermint
    0.06
    erdem
    0.06
    Activations Density 0.013%

    No Known Activations