© 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. 29805
    Prev
    Next
    INDEX
    Explanations

    This neuron is activated by Spanish words relating to acting, as well as words relating to film awards

    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
    lap
    -0.07
    ãĢģãĢģ
    -0.07
    .gdx
    -0.06
    нии
    -0.06
     kvinde
    -0.06
    strand
    -0.06
    ATEST
    -0.06
    reds
    -0.06
    ugas
    -0.06
    lia
    -0.06
    POSITIVE LOGITS
     category
    0.13
     categories
    0.12
    category
    0.10
    -category
    0.10
     kategor
    0.09
    categories
    0.09
     Categories
    0.09
    Categories
    0.08
    .category
    0.08
     Category
    0.08
    Activations Density 0.014%

    No Known Activations