© 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. 25920
    Prev
    Next
    INDEX
    Explanations

    someone trying to observe a pattern

    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
    otron
    -0.07
    ĨĴ
    -0.07
    λεÏį
    -0.06
     Remember
    -0.06
    CCCC
    -0.06
    prove
    -0.06
    zel
    -0.06
    ÑĨеÑĢ
    -0.06
    ut
    -0.06
     DropIndex
    -0.06
    POSITIVE LOGITS
     patterns
    0.21
     pattern
    0.19
     Patterns
    0.18
    Pattern
    0.16
    pattern
    0.16
     Pattern
    0.16
    patterns
    0.16
    Patterns
    0.15
    -pattern
    0.14
    _patterns
    0.14
    Activations Density 0.062%

    No Known Activations