© 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. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 28871
    Prev
    Next
    INDEX
    Explanations

    This neuron activates for a variety of things, including protein engineering, microcarriers, citations to scientific articles, and the word "obstruction," suggesting it is identifying the presence of scientific research writing.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    readcr
    -0.07
    lemn
    -0.07
    bsolute
    -0.06
    pii
    -0.06
    æł¹æľ¬
    -0.06
    drv
    -0.06
     —
    -0.06
    -0.06
    @↵
    -0.06
    EMPLARY
    -0.06
    POSITIVE LOGITS
     naï
    0.06
     khóa
    0.06
    arkan
    0.06
     '\''
    0.06
    .Ticks
    0.06
     multiplic
    0.06
    ÏĥÏĦÏĮ
    0.06
     phái
    0.06
    amma
    0.06
     ï
    0.06
    Activations Density 0.001%

    No Known Activations