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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29625
    Prev
    Next
    INDEX
    Explanations

    sentences about women and their behavior or circumstances, plus other context words such as "is", "in", and "was"

    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
    ylon
    -0.08
    меж
    -0.06
    åŃĺäºİ
    -0.06
    ilder
    -0.06
    uling
    -0.06
     мÑıÑģ
    -0.06
    alent
    -0.06
    oko
    -0.06
    опаÑģ
    -0.06
    .SO
    -0.06
    POSITIVE LOGITS
     wearing
    0.22
     wear
    0.15
     wears
    0.15
     wore
    0.15
     carrying
    0.15
     dressed
    0.14
     Wear
    0.12
    wear
    0.11
     holding
    0.10
     carry
    0.10
    Activations Density 0.030%

    No Known Activations