© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 24484
    Prev
    Next
    INDEX
    Explanations

    mentions of checking whether an equation is valid, or the results of that equation have valid properties like being an integer, distinct, or other related terms.

    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
    ubb
    -0.07
     liken
    -0.07
    must
    -0.07
     must
    -0.07
     mash
    -0.06
     Must
    -0.06
     MUST
    -0.06
    cle
    -0.06
     doomed
    -0.06
     Cle
    -0.06
    POSITIVE LOGITS
     Undo
    0.07
     INLINE
    0.06
    vsp
    0.06
    ylie
    0.06
    uche
    0.06
    StackNavigator
    0.06
     jeszcze
    0.06
    reed
    0.06
    itung
    0.06
     actually
    0.06
    Activations Density 0.095%

    No Known Activations