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. 76
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly their contributions and impacts in various fields

    oai_token-act-pair · gpt-4o-mini

    the presence of emotional or impactful language in the text, such as words expressing strong feelings or significant life events.

    oai_token-act-pair · deepseek-r1-dist-llama-70bTriggered 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
     currently
    -0.24
    缮åīį
    -0.21
    currently
    -0.19
    uai
    -0.17
    }elseif
    -0.17
    Currently
    -0.16
     presently
    -0.15
     Currently
    -0.15
    å½ĵåīį
    -0.15
    apon
    -0.15
    POSITIVE LOGITS
     always
    0.19
     Always
    0.17
    Always
    0.17
    always
    0.17
     whenever
    0.16
     Whenever
    0.15
     lifetime
    0.15
     never
    0.14
     died
    0.14
     vardı
    0.14
    Activations Density 0.185%

    No Known Activations