© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 25963
    Prev
    Next
    INDEX
    Explanations

    strings of text consisting of numbers together with words like "compute", "calculate", "let's", and "break down" suggesting some kind of arithmetic calculation is being discussed

    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
    Negative Logits
    eah
    -0.07
    iani
    -0.06
    ourg
    -0.06
    ocz
    -0.06
    atürk
    -0.06
    ialized
    -0.06
    èīĩ
    -0.06
    ÙĦÛĮس
    -0.06
    upro
    -0.06
    obre
    -0.06
    POSITIVE LOGITS
    á»ĵn
    0.07
     broken
    0.07
     breaking
    0.07
     Breaking
    0.07
     perhaps
    0.07
    -break
    0.06
    -breaking
    0.06
     break
    0.06
    Break
    0.06
    ìŀ¡
    0.06
    Activations Density 0.052%

    No Known Activations