© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 519
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and relationships in problem statements

    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
    utter
    -0.07
    elo
    -0.06
    vn
    -0.06
     foss
    -0.06
    uda
    -0.06
    овж
    -0.06
     yana
    -0.06
    resh
    -0.06
    eline
    -0.06
    ilk
    -0.06
    POSITIVE LOGITS
     during
    0.08
    BorderStyle
    0.08
    第äºĮ
    0.07
     During
    0.07
    第
    0.07
    during
    0.07
    第ä¸Ģ
    0.07
     Part
    0.07
    iban
    0.07
     第ä¸Ģ
    0.07
    Activations Density 0.043%

    No Known Activations