© 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. 25953
    Prev
    Next
    INDEX
    Explanations

    instances of reasoning, especially in a first-person context or involving problems with numbers or code

    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
    owitz
    -0.07
    ivec
    -0.06
    razier
    -0.06
    meyi
    -0.06
     Klopp
    -0.06
    .IContainer
    -0.06
    igrant
    -0.06
    dej
    -0.06
    avaÅŁ
    -0.06
    .Selenium
    -0.06
    POSITIVE LOGITS
     cannot
    0.46
     Cannot
    0.38
    cannot
    0.37
     unable
    0.36
     couldn
    0.36
    æĹłæ³ķ
    0.35
    ä¸įèĥ½
    0.35
    Cannot
    0.35
     inability
    0.33
     cant
    0.30
    Activations Density 0.102%

    No Known Activations