© 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. 25857
    Prev
    Next
    INDEX
    Explanations

    text where someone is in the middle of thinking through a problem, indicated by the use of "wait", "but", and sentence fragments.

    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
     but
    -0.34
    but
    -0.27
    ï¼Įä½Ĩ
    -0.26
     nhÆ°ng
    -0.25
     But
    -0.25
     BUT
    -0.24
    ä½Ĩ
    -0.24
    ï¼Įä½Ĩæĺ¯
    -0.24
     но
    -0.24
    But
    -0.23
    POSITIVE LOGITS
     therefore
    0.08
    BTN
    0.07
     Therefore
    0.07
    Therefore
    0.07
     hence
    0.07
    åĽłæѤ
    0.06
    ï¼ĮæīĢ以
    0.06
    æīĢ以
    0.06
     Hence
    0.06
    baru
    0.06
    Activations Density 0.600%

    No Known Activations