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-OPENR1-RES-32K
    4. 153
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and clausal transitions within complex sentences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    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
    ritz
    -0.08
     ``(
    -0.06
    uti
    -0.06
    ungan
    -0.06
    ettings
    -0.06
    #create
    -0.06
    ilver
    -0.06
    .sdk
    -0.06
    wald
    -0.06
    åIJ¹
    -0.06
    POSITIVE LOGITS
    ghan
    0.07
    ahn
    0.07
    رÙĪØª
    0.06
    ende
    0.06
    à¤Łà¤¨
    0.06
     du
    0.06
     å®
    0.06
     it
    0.06
    ighthouse
    0.06
     popular
    0.06
    Activations Density 0.085%

    No Known Activations