© 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. 2391
    Prev
    Next
    INDEX
    Explanations

    contexts and descriptions related to mathematical problem-solving and constraints

    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
    à¹īà¸Ńย
    -0.06
    796
    -0.06
    Grant
    -0.06
    buch
    -0.06
    xca
    -0.06
    QU
    -0.06
    izu
    -0.06
    ÑģÑıÑĩ
    -0.06
    InSection
    -0.05
    ClearColor
    -0.05
    POSITIVE LOGITS
     alternatives
    0.10
     instead
    0.10
    Instead
    0.09
     alternative
    0.09
     Instead
    0.09
    instead
    0.08
    ouri
    0.08
     вмеÑģÑĤ
    0.07
     alternate
    0.07
     substitute
    0.07
    Activations Density 0.155%

    No Known Activations