© 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. 23594
    Prev
    Next
    INDEX
    Explanations

    mathematical terms, theorems, and concepts, including 'ratio', 'line', 'segments', and 'points.'

    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
     Cres
    -0.07
     aforementioned
    -0.07
     this
    -0.07
    outines
    -0.06
    hle
    -0.06
    150
    -0.06
    ingly
    -0.06
     myself
    -0.06
    erset
    -0.06
     these
    -0.06
    POSITIVE LOGITS
    (*)(
    0.06
    .getOwnProperty
    0.06
    .Localization
    0.06
    ontent
    0.06
    Swagger
    0.06
    åı¦
    0.06
    поÑĢ
    0.06
     pÅĻÃŃpadnÄĽ
    0.06
    rops
    0.06
     addCriterion
    0.06
    Activations Density 0.256%

    No Known Activations