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. 58
    Prev
    Next
    INDEX
    Explanations

    references to college sports teams and related terminology

    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
    iek
    -0.15
    PARATOR
    -0.15
    ãĥĭãĤ¢
    -0.15
    ัà¸ķà¸Ļ
    -0.14
    viso
    -0.14
    .synthetic
    -0.14
    \db
    -0.14
    ório
    -0.14
    vm
    -0.14
    auty
    -0.14
    POSITIVE LOGITS
    ter
    0.14
    576
    0.14
    ufs
    0.14
    chet
    0.14
    terr
    0.13
    destination
    0.13
    arpa
    0.13
    entic
    0.13
    omba
    0.13
     than
    0.13
    Activations Density 0.217%

    No Known Activations