© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29836
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers and associated units

    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
    egen
    -0.07
    rál
    -0.07
    educt
    -0.07
    ãĥ¼ãĥĹ
    -0.06
    umlu
    -0.06
    .kwargs
    -0.06
    ienes
    -0.06
    rote
    -0.06
    Wa
    -0.06
    ekt
    -0.06
    POSITIVE LOGITS
     each
    0.28
    each
    0.25
     Each
    0.22
    Each
    0.21
     respectively
    0.20
    åIJĦ
    0.20
    .each
    0.19
     EACH
    0.18
     ê°ģê°ģ
    0.17
    _each
    0.17
    Activations Density 0.112%

    No Known Activations