© 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. 23511
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with calculations, rules, and/or existing things

    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
     Evet
    -0.06
    ietet
    -0.06
    BOVE
    -0.06
     Dün
    -0.06
    833
    -0.06
    ÑĢави
    -0.05
    amas
    -0.05
     Há»
    -0.05
    .TestTools
    -0.05
     Interior
    -0.05
    POSITIVE LOGITS
     existing
    0.10
     modified
    0.09
    æĶ¹
    0.09
     already
    0.08
     æĶ
    0.08
    already
    0.08
     modification
    0.08
    existing
    0.08
    modified
    0.08
     originally
    0.08
    Activations Density 0.110%

    No Known Activations