© 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. 3367
    Prev
    Next
    INDEX
    Explanations

    indicators of logical reasoning and contradiction

    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
    ynam
    -0.07
     Dynam
    -0.07
    ektor
    -0.07
    ditor
    -0.06
    ryn
    -0.06
    ilee
    -0.06
    iffer
    -0.06
    akov
    -0.06
    ÅĻel
    -0.06
    YNAM
    -0.06
    POSITIVE LOGITS
     now
    0.11
     Now
    0.08
    now
    0.07
    ï¼Įçİ°åľ¨
    0.07
    artz
    0.07
     agora
    0.07
    iosa
    0.06
    irth
    0.06
    Now
    0.06
    mtx
    0.06
    Activations Density 0.075%

    No Known Activations