Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 762
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences and relationships among variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L15R
    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.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
    swick
    -0.07
    quets
    -0.07
    APT
    -0.06
    ido
    -0.06
    istik
    -0.06
    infeld
    -0.06
    odor
    -0.06
     Choi
    -0.06
     anything
    -0.06
    ustum
    -0.06
    POSITIVE LOGITS
     certain
    0.08
    ä¸įåIJĮçļĦ
    0.07
    ÑĽ
    0.07
     hierarchy
    0.07
    gaard
    0.07
    óng
    0.06
     Sommer
    0.06
     Sesso
    0.06
    _hierarchy
    0.06
    ả
    0.06
    Activations Density 0.093%

    No Known Activations