© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 26272
    Prev
    Next
    INDEX
    Explanations

    sentences where logic, reasoning, inferences or realizations occur regarding how to solve a problem.

    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
     specifically
    -0.07
    wand
    -0.07
    ework
    -0.06
    utor
    -0.06
    è¿Ļæĺ¯
    -0.06
    antry
    -0.06
    κÏĦη
    -0.06
    ær
    -0.06
    ovel
    -0.06
     unl
    -0.06
    POSITIVE LOGITS
    acen
    0.08
    éĥ½ä¸į
    0.07
     ones
    0.07
    oningen
    0.06
    æ°ĹãģĮ
    0.06
     Ones
    0.06
    -pocket
    0.06
    unsch
    0.06
    otron
    0.06
     determin
    0.06
    Activations Density 0.214%

    No Known Activations