© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110640
    Prev
    Next
    INDEX
    Explanations

    medical patients

    np_max-act · gemini-2.0-flash

    The neuron highlights words naming study participants or patient cohorts (e.g. “patients,” “subjects,” “people,” “women”).

    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
     Petra
    -0.07
    _help
    -0.07
     Ups
    -0.06
    ющихся
    -0.06
    مة
    -0.06
    yang
    -0.06
     yerine
    -0.06
     errno
    -0.06
    emia
    -0.06
     altering
    -0.06
    POSITIVE LOGITS
     والت
    0.07
     */
    ↵
    0.06
    	glog
    0.06
    _INTEGER
    0.06
    scripts
    0.06
     casos
    0.06
    (___
    0.06
     found
    0.06
    '];?>"
    0.06
     GDK
    0.06
    Activations Density 0.050%

    No Known Activations