© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29420
    Prev
    Next
    INDEX
    Explanations

    text that provides actionable advice and recommendations

    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/L21R
    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.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ùĥت
    -0.06
    èįIJ
    -0.06
    æijĨ
    -0.06
    ynet
    -0.06
    jsp
    -0.06
    лиÑĪком
    -0.06
    610
    -0.06
    .wp
    -0.05
    -hook
    -0.05
    /umd
    -0.05
    POSITIVE LOGITS
     communication
    0.32
     Communication
    0.27
    communication
    0.26
    Communication
    0.25
     communicate
    0.24
     communications
    0.23
     communicates
    0.22
     communicated
    0.21
     communicating
    0.21
     comunic
    0.20
    Activations Density 0.053%

    No Known Activations