© 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. 470
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to mathematical definitions and problems involving numbers

    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
    iros
    -0.07
    CLOCKS
    -0.07
    owitz
    -0.07
    OffsetTable
    -0.06
    _Lean
    -0.06
     Cas
    -0.06
    astery
    -0.06
    ntag
    -0.06
    sworth
    -0.06
    ivityManager
    -0.06
    POSITIVE LOGITS
    ebin
    0.08
    .Fail
    0.06
    ulum
    0.06
     mine
    0.06
    mine
    0.06
    atan
    0.06
    imate
    0.06
    anon
    0.06
    йн
    0.06
    ebek
    0.06
    Activations Density 0.215%

    No Known Activations