© 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. 118099
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to technology, specifically in fields like programming and data science

    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
    tura
    -0.09
    ezi
    -0.08
    e
    -0.08
    DTV
    -0.08
    oji
    -0.07
    oyo
    -0.07
    ettle
    -0.07
    ancel
    -0.07
    /respond
    -0.06
    odash
    -0.06
    POSITIVE LOGITS
    'er
    0.07
    ï¸ı
    0.07
    /jpeg
    0.07
    aniem
    0.06
    tract
    0.06
    kening
    0.06
    ckill
    0.06
    /english
    0.06
    :s
    0.06
    OA
    0.06
    Activations Density 0.136%

    No Known Activations