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. 8090
    Prev
    Next
    INDEX
    Explanations

    references to vaccination processes and safety measures

    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
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     astr
    -0.18
     Advent
    -0.15
     éļ
    -0.14
    áct
    -0.14
    Absolute
    -0.13
     country
    -0.13
     Absolute
    -0.13
    Warnings
    -0.13
     immediately
    -0.13
     Falling
    -0.13
    POSITIVE LOGITS
     drive
    0.18
     parking
    0.15
    .drive
    0.15
    Drive
    0.15
    -drive
    0.15
    unfold
    0.15
    outs
    0.15
    ëıħ
    0.14
     Drive
    0.14
    ergus
    0.14
    Activations Density 0.037%

    No Known Activations