© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29796
    Prev
    Next
    INDEX
    Explanations

    words and formatting common in mathematical reasoning/proofs

    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
    éĤ£ä¸ª
    -0.10
    è¿Ļ个
    -0.10
    çļĦä¸Ģ个
    -0.08
    æĺ¯ä¸Ģ个
    -0.07
    ÑĭÑĪлен
    -0.07
     uveden
    -0.07
    çĹ
    -0.07
    etur
    -0.07
    нÑĭй
    -0.07
    ÑĨионного
    -0.06
    POSITIVE LOGITS
     các
    0.13
    “These
    0.12
     οι
    0.11
    "These
    0.11
     these
    0.11
     mga
    0.10
    éĤ£äºĽ
    0.10
     ÏĦÏīν
    0.10
     those
    0.10
    owych
    0.10
    Activations Density 0.072%

    No Known Activations