© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1402
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to mathematical terminology and definitions

    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
    va
    -0.07
    ingle
    -0.07
    ift
    -0.06
    OLVE
    -0.06
    arah
    -0.06
    gem
    -0.06
    ive
    -0.06
    íĮħ
    -0.06
    umm
    -0.06
    irts
    -0.06
    POSITIVE LOGITS
     such
    0.07
     ucwords
    0.07
    tir
    0.06
     Weg
    0.06
    821
    0.06
    æ°ı
    0.06
    .Err
    0.06
     ë§İìĿ´
    0.06
    Ïĥή
    0.06
    bove
    0.06
    Activations Density 0.086%

    No Known Activations