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. 11-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 8418
    Prev
    Next
    INDEX
    Explanations

    descriptions of harmful possibilities

    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/L11R
    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.11.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edia
    -0.07
    erva
    -0.06
     Cop
    -0.06
    宿
    -0.06
    ient
    -0.06
    nom
    -0.06
    amar
    -0.06
    co
    -0.06
     call
    -0.06
     calls
    -0.06
    POSITIVE LOGITS
    abbo
    0.08
    ulace
    0.07
     Easily
    0.06
    idders
    0.06
    PageIndex
    0.06
    iyon
    0.06
    ibo
    0.06
    bounce
    0.06
    _backward
    0.06
    èĭ±
    0.06
    Activations Density 0.048%

    No Known Activations