Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 129
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations involving digits and positions in a sequence

    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
    vron
    -0.07
     elevation
    -0.06
    ź
    -0.06
    ÑĢаб
    -0.06
    NDAR
    -0.06
     Abed
    -0.06
    undos
    -0.06
     اÙĦÙĤرÙĨ
    -0.06
    zier
    -0.06
    eries
    -0.06
    POSITIVE LOGITS
    SWG
    0.07
    iffe
    0.06
    ison
    0.06
    خص
    0.06
     el
    0.06
    otas
    0.06
    ontrol
    0.06
    acci
    0.06
    clusive
    0.05
    tan
    0.05
    Activations Density 0.295%

    No Known Activations