© 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. 336
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and concepts related to functions and optimization

    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
    uhn
    -0.06
    Far
    -0.06
     Rosenberg
    -0.06
     ic
    -0.06
    minating
    -0.06
    iffies
    -0.06
    ANDOM
    -0.06
     Far
    -0.06
     underlying
    -0.06
    iac
    -0.06
    POSITIVE LOGITS
    iÃŁ
    0.06
    atk
    0.06
    üss
    0.06
    isson
    0.06
    Callable
    0.06
    [vi
    0.06
    agus
    0.06
    aternity
    0.06
    lrt
    0.06
    urrenc
    0.06
    Activations Density 0.089%

    No Known Activations