Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 148
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations involving variables and their relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.10
    azzi
    -0.07
    -пÑĢав
    -0.07
    ë¨
    -0.07
    /loose
    -0.06
    insky
    -0.06
    æĹıèĩªæ²»
    -0.06
    лÑĥг
    -0.06
    ÙĪÙĤت
    -0.06
    enko
    -0.06
    POSITIVE LOGITS
     etc
    0.08
    sam
    0.07
    hir
    0.07
     Sam
    0.07
    etc
    0.06
    andex
    0.06
     mixed
    0.06
    annels
    0.06
     otherwise
    0.06
     forth
    0.06
    Activations Density 0.042%

    No Known Activations