© 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. 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. 44519
    Prev
    Next
    INDEX
    Explanations

    cesarean section/delivery

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on split‐up tokens of “ces are an section” (i.e. C-section/cesarean section) and thus detects mentions of cesarean deliveries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to cesarean sections in maternal health discussions.

    oai_token-act-pair · gpt-4o-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
    やす
    -0.06
    com
    -0.06
    descending
    -0.06
    	iter
    -0.06
    verity
    -0.06
    -0.06
     vidéo
    -0.06
     chimpan
    -0.06
    Depart
    -0.06
    *cos
    -0.06
    POSITIVE LOGITS
    賽
    0.07
     MP
    0.07
     ج
    0.07
     مذ
    0.06
    +"&
    0.06
    лось
    0.06
    ุทธ
    0.06
    \$
    0.06
    )',
    0.06
    AGES
    0.06
    Activations Density 0.008%

    No Known Activations