© 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. 24424
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and discussion

    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
    Harness
    -0.07
    (::
    -0.06
    ообÑĢаз
    -0.06
    باز
    -0.06
    üb
    -0.06
    ToLocal
    -0.06
    inth
    -0.06
    adge
    -0.06
    hoe
    -0.06
    fragistics
    -0.06
    POSITIVE LOGITS
    iri
    0.09
    ISCO
    0.07
    iring
    0.06
     Gab
    0.06
    elled
    0.06
    aka
    0.06
     ambit
    0.06
    -Bar
    0.06
    ONTAL
    0.06
    irs
    0.06
    Activations Density 0.271%

    No Known Activations