© 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. 390
    Prev
    Next
    INDEX
    Explanations

    instances of the word "specific" and its variants, indicating a focus on detailed or particular examples

    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
    ĮĢ
    -0.07
    anche
    -0.07
    our
    -0.07
     entire
    -0.07
    ych
    -0.07
    ses
    -0.07
    anas
    -0.07
    ibs
    -0.07
    cn
    -0.07
    ous
    -0.07
    POSITIVE LOGITS
    ially
    0.10
    -purpose
    0.09
    ;y
    0.09
    ities
    0.08
    tons
    0.08
    pants
    0.08
    ity
    0.08
    /general
    0.07
     sayıda
    0.07
    -minded
    0.07
    Activations Density 0.052%

    No Known Activations