© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29908
    Prev
    Next
    INDEX
    Explanations

    passages that include the word "knight" within a logical argument that contains the words 'if', 'then', or 'no'

    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
     Doll
    -0.08
     Gust
    -0.07
     lick
    -0.06
     grounding
    -0.06
     funk
    -0.06
     grounded
    -0.06
     Ts
    -0.06
    ora
    -0.06
     ground
    -0.06
     gem
    -0.06
    POSITIVE LOGITS
     knight
    0.12
     knights
    0.12
     Arthur
    0.12
     Camel
    0.11
     Knight
    0.10
    Arthur
    0.10
     Knights
    0.10
    Knight
    0.10
     tournaments
    0.10
    Sir
    0.09
    Activations Density 0.090%

    No Known Activations