© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1124
    Prev
    Next
    INDEX
    Explanations

    mathematical patterns or expressions, specifically related to solving equations

    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
    اÙĩÙħ
    -0.06
    FINE
    -0.06
    ey
    -0.06
    ALTH
    -0.06
    ibName
    -0.06
    är
    -0.06
    ia
    -0.06
    iyi
    -0.06
    otten
    -0.05
    emento
    -0.05
    POSITIVE LOGITS
    ursor
    0.06
    ánh
    0.06
    _live
    0.06
    .partition
    0.06
    bes
    0.06
     Gü
    0.06
    ìļ¸
    0.06
    uat
    0.05
    urga
    0.05
     NTN
    0.05
    Activations Density 0.026%

    No Known Activations