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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1713
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and relationships in sequences

    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
    vel
    -0.06
     diren
    -0.06
    kuk
    -0.06
    arend
    -0.06
    rench
    -0.06
    sg
    -0.05
    riday
    -0.05
    омен
    -0.05
    bes
    -0.05
    OLUMN
    -0.05
    POSITIVE LOGITS
     Banc
    0.06
    omap
    0.06
    .Undef
    0.06
     ëĭ¤ìļ´ë°Ľê¸°
    0.06
    -overlay
    0.06
    ศาสà¸ķร
    0.06
    -LAST
    0.06
    ãĥ©ãĥ¼
    0.06
    Clr
    0.06
    haps
    0.06
    Activations Density 0.262%

    No Known Activations