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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 26952
    Prev
    Next
    INDEX
    Explanations

    sentences regarding some hypothetical or potential outcome or sentiment

    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
    iti
    -0.06
    inke
    -0.06
    ryo
    -0.06
    nga
    -0.06
    æ³Ľ
    -0.06
    adal
    -0.06
    lod
    -0.06
    å¿ħè¦ģ
    -0.06
    ingleton
    -0.06
    lim
    -0.06
    POSITIVE LOGITS
     nice
    0.09
     interess
    0.08
     ideal
    0.07
     benefit
    0.07
     great
    0.07
     interesting
    0.07
     novel
    0.07
    nice
    0.07
     interest
    0.07
     rem
    0.07
    Activations Density 0.024%

    No Known Activations