© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and problem-solving 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
    eck
    -0.06
     Pins
    -0.06
    üs
    -0.06
     bitir
    -0.06
    rics
    -0.06
    каж
    -0.06
    chw
    -0.06
    ele
    -0.06
    ãģİ
    -0.06
    év
    -0.06
    POSITIVE LOGITS
     each
    0.09
    åĪĨåĪ«
    0.08
     respective
    0.07
     different
    0.07
     Option
    0.07
     scenario
    0.07
     Each
    0.07
     differing
    0.07
     scenarios
    0.07
    each
    0.07
    Activations Density 0.028%

    No Known Activations