© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29030
    Prev
    Next
    INDEX
    Explanations

    conditional clauses involving "would," "are," and "is"

    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
    kus
    -0.06
    orris
    -0.06
    istrate
    -0.06
    ape
    -0.06
    roc
    -0.05
    odie
    -0.05
    ÏĦά
    -0.05
    iyon
    -0.05
    uppe
    -0.05
    Curr
    -0.05
    POSITIVE LOGITS
     previously
    0.40
     formerly
    0.37
     former
    0.33
     Previously
    0.32
    formerly
    0.31
    Previously
    0.30
     Former
    0.27
     once
    0.26
    Former
    0.26
     previous
    0.25
    Activations Density 0.095%

    No Known Activations