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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58154
    Prev
    Next
    INDEX
    Explanations

    pregnancy and birth

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases tied to pregnancy care—especially prenatal appointments, midwife visits, and related maternal health terms.

    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
    rea
    -0.06
     협
    -0.06
     답변
    -0.06
    zeros
    -0.06
     Pemb
    -0.06
     추가
    -0.06
    .TIME
    -0.06
    ının
    -0.06
    457
    -0.06
    แบ
    -0.06
    POSITIVE LOGITS
    くれる
    0.07
     -------
    0.07
     Album
    0.06
    -provider
    0.06
    _lambda
    0.06
    .internal
    0.06
     замі
    0.06
    ิน
    0.06
     accelerated
    0.06
     England
    0.06
    Activations Density 0.051%

    No Known Activations