© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 3378
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical cases or conditions in problem-solving contexts

    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
    Negative Logits
    Brad
    -0.07
    _FOREACH
    -0.06
    prit
    -0.06
    оÑĢож
    -0.06
    /cgi
    -0.06
    /logger
    -0.06
    ÑĪов
    -0.06
    Votes
    -0.06
    ellow
    -0.06
    าะ
    -0.06
    POSITIVE LOGITS
    langs
    0.07
     second
    0.07
    cken
    0.07
    å®ı
    0.06
    agen
    0.06
    rais
    0.06
    ays
    0.06
     cin
    0.06
    orial
    0.06
     convention
    0.06
    Activations Density 0.057%

    No Known Activations