© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 255
    Prev
    Next
    INDEX
    Explanations

    logical implications and conditions in mathematical statements

    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
    YNAM
    -0.07
    ickers
    -0.06
    IDO
    -0.06
     Singap
    -0.06
     Shepard
    -0.06
    uji
    -0.06
    yas
    -0.06
    лаз
    -0.06
    ابت
    -0.05
    _toggle
    -0.05
    POSITIVE LOGITS
    bourg
    0.08
    wort
    0.07
    AVA
    0.07
    धर
    0.06
    away
    0.06
    æĿIJ
    0.06
    ottes
    0.06
    edBy
    0.06
    amps
    0.06
    oped
    0.06
    Activations Density 0.033%

    No Known Activations