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-OPENR1-RES-32K
    4. 149
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical problem-solving

    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
    weetalert
    -0.07
    ipmap
    -0.07
    ä¸įåŃĺåľ¨
    -0.06
    Äĥm
    -0.06
    MethodInfo
    -0.06
    ldkf
    -0.06
    eway
    -0.06
     addCriterion
    -0.06
    eways
    -0.06
    inte
    -0.06
    POSITIVE LOGITS
    amu
    0.07
    erus
    0.07
     é¡
    0.07
    olo
    0.06
    CV
    0.06
    unu
    0.06
    illance
    0.06
    ired
    0.06
    slash
    0.06
     clear
    0.06
    Activations Density 0.056%

    No Known Activations