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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1598
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and relationships involving numbers and equations

    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
    ucha
    -0.07
    à¹ĥ
    -0.06
    ugg
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    ten
    -0.05
     Shuttle
    -0.05
    ubah
    -0.05
    tn
    -0.05
    rer
    -0.05
    indle
    -0.05
    POSITIVE LOGITS
     these
    0.22
     These
    0.19
    These
    0.18
    these
    0.18
    è¿ĻäºĽ
    0.17
     THESE
    0.14
     tÄĽchto
    0.13
     ÑįÑĤиÑħ
    0.12
     bunları
    0.12
     them
    0.12
    Activations Density 0.097%

    No Known Activations