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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 622
    Prev
    Next
    INDEX
    Explanations

    mathematical equivalences and relationships

    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
    lez
    -0.07
     Cong
    -0.06
    immer
    -0.06
    endez
    -0.06
    tright
    -0.06
    .cf
    -0.06
    levation
    -0.06
    apor
    -0.06
     æĻ®
    -0.06
    RICT
    -0.05
    POSITIVE LOGITS
     included
    0.08
     acceptable
    0.07
    .Aggressive
    0.07
     inclusion
    0.07
     plenty
    0.07
    ampus
    0.06
    oleon
    0.06
    teri
    0.06
     inclusive
    0.06
    خر
    0.06
    Activations Density 0.033%

    No Known Activations