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. 1496
    Prev
    Next
    INDEX
    Explanations

    references to legal repercussions and actions regarding business operations, especially involving federal regulations

    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
    berman
    -0.14
    cles
    -0.14
    عاÙĨ
    -0.13
    COPY
    -0.13
    266
    -0.13
    immel
    -0.13
    -det
    -0.13
    lient
    -0.13
    unter
    -0.13
    inya
    -0.13
    POSITIVE LOGITS
     future
    0.19
    future
    0.16
    ä¿
    0.15
    à¸ģรà¸ĵ
    0.15
     privileges
    0.15
    <TKey
    0.14
    rowad
    0.14
    cker
    0.14
     access
    0.14
    éģ¿
    0.14
    Activations Density 0.086%

    No Known Activations