© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29827
    Prev
    Next
    INDEX
    Explanations

    words related to falling, collapsing, or being in a lowered position

    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
    ION
    -0.06
    à¹īà¸Ļà¸Ĺ
    -0.06
    pais
    -0.06
    ÑĢÑĸд
    -0.06
    ä¸ĬäºĨ
    -0.06
     hâl
    -0.06
    orgen
    -0.06
    енка
    -0.06
    chop
    -0.06
    ridge
    -0.06
    POSITIVE LOGITS
     into
    0.12
     falling
    0.10
     onto
    0.10
     falls
    0.10
    èIJ½
    0.10
     INTO
    0.09
     Falling
    0.08
     down
    0.08
    fall
    0.08
    into
    0.08
    Activations Density 0.017%

    No Known Activations