© 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. 23581
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate inside math equations

    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
    ãģĭãģij
    -0.06
    enz
    -0.06
    (s
    -0.06
    OrCreate
    -0.06
     nailed
    -0.06
    або
    -0.06
    çļĦæĺ¯
    -0.06
    ±Ð¾ÑĤ
    -0.06
     Stein
    -0.05
     ::
    -0.05
    POSITIVE LOGITS
    .central
    0.07
    KY
    0.06
    ikit
    0.06
    ecast
    0.06
    rane
    0.06
    infer
    0.06
    .removeAll
    0.06
    reeNode
    0.06
    oso
    0.06
    andest
    0.06
    Activations Density 0.047%

    No Known Activations