© 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. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23959
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in mathematical reasoning within word problems, with an emphasis on the manipulation of numbers and problem-solving steps

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L17R
    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.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ead
    -0.07
     Stevenson
    -0.06
    forth
    -0.06
    анÑĤаж
    -0.06
    /non
    -0.06
    leon
    -0.06
    dbcTemplate
    -0.06
    KHR
    -0.05
    ÐIJÑĢÑħÑĸв
    -0.05
    us
    -0.05
    POSITIVE LOGITS
    جاد
    0.08
    iazza
    0.06
    _PREFIX
    0.06
    طر
    0.06
    ovenant
    0.06
    گرد
    0.06
     disadv
    0.06
    ali
    0.06
    _CN
    0.05
     åıĮ
    0.05
    Activations Density 0.307%

    No Known Activations