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. 4500
    Prev
    Next
    INDEX
    Explanations

    mentions of democratic concepts and terms related to governance

    oai_token-act-pair · gpt-4o-mini

    references to democracy and democratic principles.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @zonunmawiazadeng7
    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
    itional
    -0.17
    ernational
    -0.15
    borne
    -0.15
    omer
    -0.15
    iph
    -0.15
    ividual
    -0.14
    iff
    -0.14
    ÑĨеÑģ
    -0.14
    çī©
    -0.14
    omo
    -0.14
    POSITIVE LOGITS
    stration
    0.18
    aurus
    0.14
    izedName
    0.14
     Deg
    0.14
    strate
    0.14
    atically
    0.14
    687
    0.14
    Ñĩил
    0.14
    ikan
    0.14
    ically
    0.14
    Activations Density 0.042%

    No Known Activations