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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29497
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and symbols within explanations or examples on mathematical topics

    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/L21R
    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.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    znám
    -0.07
    roj
    -0.07
    vido
    -0.06
    ëĿ¼ëıĦ
    -0.06
     erotico
    -0.06
     ãģį
    -0.06
    pras
    -0.06
    shall
    -0.06
    Ìĥ
    -0.06
    gom
    -0.06
    POSITIVE LOGITS
     here
    0.11
    Here
    0.07
    bes
    0.07
    æķ°åŃĹ
    0.06
    here
    0.06
    _here
    0.06
     Here
    0.06
     among
    0.06
     present
    0.06
     Erg
    0.06
    Activations Density 0.117%

    No Known Activations