© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23678
    Prev
    Next
    INDEX
    Explanations

    equations and equation-related formatting in LaTeX

    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
    SORT
    -0.06
    957
    -0.06
    onso
    -0.06
    agem
    -0.06
    лаÑĪ
    -0.06
    itler
    -0.06
    é¢ĺ
    -0.06
     sho
    -0.06
    lém
    -0.06
     thing
    -0.06
    POSITIVE LOGITS
    addon
    0.07
    zers
    0.07
    ħn
    0.06
    itals
    0.06
    νά
    0.06
    _sy
    0.06
    ÛĮÛĮÙĨ
    0.06
    OwnProperty
    0.06
    _pll
    0.06
     Engel
    0.06
    Activations Density 0.624%

    No Known Activations