© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 387
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and constraints involving arrangements and permutations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĥлÑİ
    -0.08
    own
    -0.06
    bersome
    -0.06
    umer
    -0.06
    ashtra
    -0.06
    alet
    -0.06
    ória
    -0.06
    ợ
    -0.06
    erken
    -0.06
    IPLE
    -0.06
    POSITIVE LOGITS
     whether
    0.10
     question
    0.09
     potentially
    0.09
     either
    0.09
     versus
    0.08
     or
    0.08
     potential
    0.08
     Whether
    0.08
     possibly
    0.08
     vs
    0.07
    Activations Density 0.074%

    No Known Activations