© 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. 28703
    Prev
    Next
    INDEX
    Explanations

    attempts to solve complex math or logic problems

    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
     Thornton
    -0.06
     ogs
    -0.06
     Ñģами
    -0.06
    whereIn
    -0.06
     sama
    -0.06
     åıĤ
    -0.06
    برد
    -0.06
    两个
    -0.05
    rak
    -0.05
    posable
    -0.05
    POSITIVE LOGITS
    æĺ¯ä¸Ģ个
    0.07
    erce
    0.07
    åıĬåħ¶
    0.07
    æĺ¯ä¸ª
    0.07
    ä½ľä¸º
    0.07
    antas
    0.06
    Anywhere
    0.06
    è¿Ļæĺ¯
    0.06
     plus
    0.06
    ãĤĬãģ¨
    0.06
    Activations Density 0.058%

    No Known Activations