© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54043
    Prev
    Next
    INDEX
    Explanations

    labor and contractions

    np_max-act · gemini-2.0-flash

    This neuron activates on technical childbirth vocabulary, especially words naming stages and actions of labor and delivery (e.g. labor, contractions, cervix dilation, birth, postpartum care).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     آمد
    -0.06
     dysfunction
    -0.06
    _meter
    -0.06
    rails
    -0.06
    rics
    -0.06
    armacy
    -0.06
     //.
    -0.06
     Iss
    -0.06
     WPARAM
    -0.06
    ег
    -0.06
    POSITIVE LOGITS
     marzo
    0.06
     Honour
    0.06
     hak
    0.06
     qualify
    0.06
     erh
    0.06
    \Mail
    0.06
     Terra
    0.06
     IPCC
    0.06
    .big
    0.06
     innov
    0.06
    Activations Density 0.003%

    No Known Activations