© 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. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23337
    Prev
    Next
    INDEX
    Explanations

    the relationships between family members, especially mothers and daughters in the context of movie characters and their real-life counterparts

    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/L17R
    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.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endid
    -0.06
     Äiju
    -0.06
    egas
    -0.06
    ajas
    -0.06
    IDO
    -0.06
    sam
    -0.06
    inos
    -0.06
    伯
    -0.06
    éľ
    -0.06
    zac
    -0.06
    POSITIVE LOGITS
     character
    0.14
     characters
    0.14
     fictional
    0.13
    characters
    0.11
     Characters
    0.11
     fiction
    0.11
     Fiction
    0.10
     fict
    0.10
    fiction
    0.10
    Characters
    0.10
    Activations Density 0.053%

    No Known Activations