© 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. 44590
    Prev
    Next
    INDEX
    Explanations

    nursing

    np_max-act · gemini-2.0-flash

    The neuron is triggered by terms referring to nursing and related professional practice concepts (e.g., nursing, nurse, practice, clinical, professional).

    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
     navCtrl
    -0.06
     HttpServletRequest
    -0.06
     Yuk
    -0.06
    쟁
    -0.06
    Deleted
    -0.05
     bug
    -0.05
     sacrificing
    -0.05
     trajectory
    -0.05
    .wait
    -0.05
    vim
    -0.05
    POSITIVE LOGITS
     msec
    0.07
     governmental
    0.07
    manı
    0.07
     Велик
    0.06
    -effective
    0.06
     qualifies
    0.06
     \'
    0.06
    .slice
    0.06
     návr
    0.06
    eso
    0.06
    Activations Density 0.038%

    No Known Activations