© 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. 813
    Prev
    Next
    INDEX
    Explanations

    terms related to mutual relationships and orthogonal relationships in mathematical 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
    Not in Any Lists

    No Comments

    Negative Logits
    612
    -0.08
    lights
    -0.08
    .onView
    -0.07
    ãģĵãģĿ
    -0.07
    pack
    -0.07
    ernals
    -0.06
    ling
    -0.06
    smith
    -0.06
    agnost
    -0.06
    ittel
    -0.06
    POSITIVE LOGITS
    s
    0.08
    leted
    0.07
    ities
    0.07
    mente
    0.06
    hood
    0.06
     lap
    0.06
     conv
    0.06
    adele
    0.06
    ÅĽcie
    0.06
    pliers
    0.06
    Activations Density 0.031%

    No Known Activations