Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 61
    Prev
    Next
    INDEX
    Explanations

    punctuations, specifically commas and colons

    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
    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
    azon
    -0.07
    s
    -0.07
    sik
    -0.07
    eniable
    -0.06
    errated
    -0.06
    eless
    -0.06
    heritance
    -0.06
    udio
    -0.06
    owing
    -0.06
    serrat
    -0.06
    POSITIVE LOGITS
    odore
    0.10
    adays
    0.08
    atomy
    0.07
    ese
    0.07
    оди
    0.06
    atre
    0.06
    #ab
    0.06
    üstü
    0.06
    Ā
    0.06
    struments
    0.06
    Activations Density 0.153%

    No Known Activations