© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 467
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially commas and closing parentheses, suggesting a focus on structuring information

    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
     Hyp
    -0.06
    zew
    -0.06
    enci
    -0.06
    üzel
    -0.06
    .GUI
    -0.06
    anian
    -0.06
     incre
    -0.06
    ĭ
    -0.06
    apore
    -0.06
    ongyang
    -0.06
    POSITIVE LOGITS
    imately
    0.06
    éϤäºĨ
    0.06
    ewith
    0.06
     hut
    0.06
     already
    0.06
    alchemy
    0.06
    igen
    0.06
     saat
    0.06
    518
    0.06
    oster
    0.06
    Activations Density 0.100%

    No Known Activations