© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1310
    Prev
    Next
    INDEX
    Explanations

    relationships between geometric shapes and their positions relative to one another

    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
    endi
    -0.06
    ãĤ´ãĥª
    -0.06
    òng
    -0.06
    isel
    -0.06
    >NN
    -0.06
    svn
    -0.06
    irez
    -0.06
     sâu
    -0.06
    adem
    -0.06
    огод
    -0.06
    POSITIVE LOGITS
     outside
    0.25
     Outside
    0.20
    å¤ĸ
    0.20
    Outside
    0.19
    outside
    0.19
     external
    0.17
     outer
    0.15
     exterior
    0.14
     å¤ĸ
    0.14
     buiten
    0.14
    Activations Density 0.052%

    No Known Activations