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. 139
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement and positional relationships

    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
    alat
    -0.06
    wahl
    -0.06
    327
    -0.06
    helm
    -0.06
    ingle
    -0.06
     ÏĢεÏģιÏĥÏĥÏĮÏĦε
    -0.06
    lak
    -0.06
    oren
    -0.06
    ighth
    -0.06
    важ
    -0.05
    POSITIVE LOGITS
    estring
    0.07
    ETA
    0.07
    azaar
    0.06
    лиж
    0.06
     Sher
    0.06
    ÅĽcie
    0.06
     попада
    0.06
    Ùĥرة
    0.06
    opard
    0.06
    bette
    0.06
    Activations Density 0.057%

    No Known Activations