© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 30010
    Prev
    Next
    INDEX
    Explanations

    words associated with mathematical reasoning like "so," "therefore," "in," "for," "part," and "proof."

    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
    937
    -0.06
    257
    -0.06
    iro
    -0.06
     equ
    -0.06
    -0.06
    agger
    -0.06
    ita
    -0.05
    625
    -0.05
    inte
    -0.05
     ↵
    -0.05
    POSITIVE LOGITS
     general
    0.41
    general
    0.33
     général
    0.28
    ä¸ĢèĪ¬
    0.27
     generalize
    0.26
     generic
    0.26
    -general
    0.26
     generally
    0.26
    _general
    0.25
    General
    0.25
    Activations Density 0.146%

    No Known Activations