Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 138
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and problem-solving references

    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
     [
    -0.09
    ety
    -0.08
     (
    -0.08
     An
    -0.07
    ,
    -0.07
    oid
    -0.07
    An
    -0.07
    oids
    -0.07
     "
    -0.07
     can
    -0.07
    POSITIVE LOGITS
    autiful
    0.07
    .DataAccess
    0.07
    utherland
    0.07
     addCriterion
    0.07
    Ĩµ
    0.06
     onLoad
    0.06
    ÑĢÑıдÑĥ
    0.06
    ίνη
    0.06
    yar
    0.06
    stro
    0.06
    Activations Density 0.045%

    No Known Activations