© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59240
    Prev
    Next
    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to patients’ families and caregivers, flagging mentions of family involvement or caregiver roles.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     hungry
    -0.07
    _STRING
    -0.06
     punched
    -0.06
    _wait
    -0.06
     universally
    -0.06
    “Well
    -0.06
    |string
    -0.06
    _OUTPUT
    -0.06
    opes
    -0.06
    尖
    -0.06
    POSITIVE LOGITS
     superv
    0.07
    .btnSave
    0.06
     примі
    0.06
    .AdapterView
    0.06
     Environmental
    0.06
     anticipate
    0.06
     Tham
    0.06
    paren
    0.06
     mandatory
    0.06
     imperialism
    0.06
    Activations Density 0.015%

    No Known Activations