© 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. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 23431
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and logical reasoning

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L17R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antha
    -0.07
    $__
    -0.06
    ÏĢÎŃ
    -0.06
     Explicit
    -0.06
    _marshall
    -0.06
    fal
    -0.06
     cass
    -0.06
     srd
    -0.06
    ÑĢÑĥÑĩ
    -0.06
    _Insert
    -0.06
    POSITIVE LOGITS
     meaningful
    0.12
    meaning
    0.09
     meaning
    0.09
     undefined
    0.09
    undefined
    0.08
     valid
    0.08
     Meaning
    0.08
     validity
    0.07
     meaningless
    0.07
     defined
    0.07
    Activations Density 0.126%

    No Known Activations