© 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. 29182
    Prev
    Next
    INDEX
    Explanations

    words or phrases containing "homeless", "out", "rich", or "employed" (especially hyphenated)

    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
    ald
    -0.08
    uren
    -0.07
    illow
    -0.07
    uzey
    -0.07
    clude
    -0.07
    enate
    -0.07
    aden
    -0.06
    istrovstvÃŃ
    -0.06
    pon
    -0.06
    unque
    -0.06
    POSITIVE LOGITS
    ness
    0.15
     individuals
    0.15
     person
    0.12
     persons
    0.11
    nes
    0.11
     ones
    0.10
    NESS
    0.10
     people
    0.10
     Individuals
    0.09
     members
    0.08
    Activations Density 0.059%

    No Known Activations