© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 218
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical operations and comparisons

    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
    eree
    -0.06
    ære
    -0.06
    ạnh
    -0.06
    ç³
    -0.06
    odia
    -0.06
    eniable
    -0.06
    431
    -0.06
     Kramer
    -0.06
    ´
    -0.05
    "."
    -0.05
    POSITIVE LOGITS
     both
    0.27
    both
    0.24
     Both
    0.22
    Both
    0.22
     either
    0.19
     BOTH
    0.18
     neither
    0.17
     både
    0.17
    _both
    0.16
    either
    0.15
    Activations Density 0.091%

    No Known Activations