© 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. 29574
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions using letters 'a', 'k', 's', 't', 'x', 'y', and numbers

    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
    ursal
    -0.06
    isle
    -0.06
    StreamWriter
    -0.06
    ç´ł
    -0.06
    libs
    -0.06
    parer
    -0.06
     Marcus
    -0.06
    «
    -0.06
    DIM
    -0.06
    ä¸Ķ
    -0.05
    POSITIVE LOGITS
     zero
    0.17
    -zero
    0.14
    0
    0.14
     Zero
    0.13
     zeroes
    0.12
    Zero
    0.12
    .zero
    0.12
    zero
    0.11
     zeros
    0.11
    _zero
    0.11
    Activations Density 0.129%

    No Known Activations