© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 345
    Prev
    Next
    INDEX
    Explanations

    text related to mathematical expressions, specifically quadratic equations and their properties

    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
    anders
    -0.07
    ãĥ³ãĥĶ
    -0.06
     Abrams
    -0.06
    Mounted
    -0.06
    jets
    -0.06
     اÙĦعربÙĬ
    -0.06
    .xhtml
    -0.06
     Abbey
    -0.06
     ëĭ¤ìļ´ë°Ľê¸°
    -0.06
     fare
    -0.06
    POSITIVE LOGITS
     somehow
    0.07
     means
    0.06
    ennon
    0.06
     Sür
    0.06
    annon
    0.06
    åħ¨éĿ¢
    0.06
    à¹īà¸Ļà¸Ĺ
    0.06
    691
    0.06
    366
    0.06
     Hoover
    0.06
    Activations Density 0.095%

    No Known Activations