© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29658
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning and justification

    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
    ierge
    -0.06
    ozilla
    -0.06
    uw
    -0.05
    иÑĤоÑĢ
    -0.05
    ArrayOf
    -0.05
    ÏĦί
    -0.05
    ernity
    -0.05
    ëĭ
    -0.05
     sek
    -0.05
    SimpleName
    -0.05
    POSITIVE LOGITS
     formal
    0.35
     official
    0.31
     formally
    0.28
    æŃ£å¼ı
    0.28
     Formal
    0.27
     Official
    0.26
     officially
    0.26
    official
    0.25
    Official
    0.25
    å®ĺæĸ¹
    0.23
    Activations Density 0.240%

    No Known Activations