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. 73
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    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
    423
    -0.06
     reife
    -0.06
    δο
    -0.06
    olik
    -0.06
     refl
    -0.05
     komment
    -0.05
    irma
    -0.05
    Wer
    -0.05
     ogl
    -0.05
    WB
    -0.05
    POSITIVE LOGITS
    ynos
    0.06
    itbart
    0.06
    .FontStyle
    0.06
    ardon
    0.06
    gard
    0.06
    $MESS
    0.06
    #ac
    0.06
    सल
    0.06
    [frame
    0.06
     RuntimeMethod
    0.06
    Activations Density 0.816%

    No Known Activations