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. 8408
    Prev
    Next
    INDEX
    Explanations

    mentions of individual letters

    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
     beneath
    -0.06
    \CMS
    -0.06
    hip
    -0.06
    neath
    -0.06
     below
    -0.06
    поÑĢ
    -0.06
    Ctl
    -0.06
    ño
    -0.06
     linear
    -0.06
    forth
    -0.06
    POSITIVE LOGITS
     letters
    0.07
     letter
    0.07
    _letter
    0.07
    fortawesome
    0.06
    icals
    0.06
    ãĥĶãĥ¼
    0.06
    ichel
    0.06
    _dash
    0.06
    atab
    0.06
    deserialize
    0.06
    Activations Density 0.336%

    No Known Activations