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. 8101
    Prev
    Next
    INDEX
    Explanations

    situations involving legal issues and advice regarding criminal justice

    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
    ailer
    -0.17
    achable
    -0.16
    ácil
    -0.15
    swire
    -0.14
     prem
    -0.14
    loi
    -0.14
    cuador
    -0.13
    ذر
    -0.13
    obo
    -0.13
    ViewById
    -0.13
    POSITIVE LOGITS
     tips
    0.19
     suddenly
    0.18
    еж
    0.17
     Tips
    0.17
    .ribbon
    0.15
    590
    0.15
     sudden
    0.14
    entric
    0.14
     Suddenly
    0.14
    Occurred
    0.14
    Activations Density 0.122%

    No Known Activations