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-SLIMPJ-RES-32K
    4. 1668
    Prev
    Next
    INDEX
    Explanations

    elements related to business planning and development

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isay
    -0.17
    annis
    -0.15
    -coded
    -0.15
     persön
    -0.15
    ANEL
    -0.14
    à¸ł
    -0.14
    sted
    -0.14
    tiler
    -0.14
    unami
    -0.13
    ứng
    -0.13
    POSITIVE LOGITS
     Nut
    0.14
     before
    0.14
     plan
    0.14
     clearly
    0.14
     Scotia
    0.14
    306
    0.14
     realistic
    0.14
     placeholders
    0.14
    before
    0.14
    278
    0.13
    Activations Density 0.166%

    No Known Activations