© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    queries about specific cases or conditions in a problem-solving context

    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
    翼
    -0.06
     Garr
    -0.06
     new
    -0.06
    .si
    -0.06
    ugo
    -0.06
    ByVersion
    -0.06
     conserv
    -0.06
    illard
    -0.06
     Rag
    -0.06
    bah
    -0.06
    POSITIVE LOGITS
    碰
    0.08
    afd
    0.07
    VRT
    0.07
    ilde
    0.07
     particular
    0.07
    оба
    0.06
    inkel
    0.06
    iot
    0.06
     ÏĢεÏģι
    0.06
    egative
    0.06
    Activations Density 0.032%

    No Known Activations