© 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. 26091
    Prev
    Next
    INDEX
    Explanations

    math terminology embedded in an explanation of 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
    rome
    -0.07
     combinations
    -0.06
    .mas
    -0.06
    adora
    -0.06
    ipy
    -0.06
    icens
    -0.06
     calc
    -0.06
    ita
    -0.06
    ActionBar
    -0.06
    aret
    -0.06
    POSITIVE LOGITS
     match
    0.12
     matching
    0.12
    åĮ¹
    0.11
     matches
    0.11
    .Match
    0.10
    Matching
    0.10
     Matching
    0.10
    Match
    0.10
     Match
    0.10
    (match
    0.09
    Activations Density 0.180%

    No Known Activations