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. 1665
    Prev
    Next
    INDEX
    Explanations

    references to certain unit measurements or scientific designations

    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
    ses
    -0.16
    Ø©
    -0.14
    á»ı
    -0.14
    mium
    -0.14
    ients
    -0.13
    eru
    -0.12
    oÄį
    -0.12
    arrants
    -0.12
    ä¾
    -0.12
     drain
    -0.11
    POSITIVE LOGITS
    odore
    0.24
    atre
    0.21
    etheless
    0.21
    adays
    0.20
    apolis
    0.19
    hiba
    0.17
    oret
    0.17
    atchewan
    0.16
    опаÑģ
    0.15
    oretical
    0.15
    Activations Density 0.316%

    No Known Activations