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. 1474
    Prev
    Next
    INDEX
    Explanations

    phrases related to gift options and occasions

    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
    #
    -0.17
    unga
    -0.15
     Belmont
    -0.14
    felt
    -0.14
    ette
    -0.14
    mb
    -0.14
    _IOS
    -0.14
    ãĤ¤ãĥ«
    -0.14
     aray
    -0.14
    ptal
    -0.14
    POSITIVE LOGITS
     gift
    0.42
     gifts
    0.34
     Gift
    0.34
    gift
    0.31
    Gift
    0.28
     Gifts
    0.27
     Christmas
    0.23
     christmas
    0.21
    _gift
    0.20
     gifted
    0.20
    Activations Density 0.037%

    No Known Activations