© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 23476
    Prev
    Next
    INDEX
    Explanations

    text describing the calculations for creating a grid including "toothpicks", "lines", "rows", and "columns".

    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/L17R
    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.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    busters
    -0.07
    .qq
    -0.07
    essler
    -0.06
    егод
    -0.06
    æĿ¾
    -0.06
    mong
    -0.06
    abra
    -0.06
     renewed
    -0.05
     wings
    -0.05
     prez
    -0.05
    POSITIVE LOGITS
     number
    0.09
    次æķ°
    0.07
    number
    0.07
     numberOf
    0.07
    aucoup
    0.07
     NumberOf
    0.06
     doubled
    0.06
     número
    0.06
    NumberOf
    0.06
    ATS
    0.06
    Activations Density 0.533%

    No Known Activations