© 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 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. 15-RESID-POST-AA
    11. 26105
    Prev
    Next
    INDEX
    Explanations

    clinical, patient

    np_max-act · gemini-2.0-flash

    It detects clinical/medical context — passages discussing patient-focused studies, treatments, or clinical settings.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جيل
    -0.07
     challenging
    -0.06
     příprav
    -0.06
    853
    -0.06
    家庭
    -0.06
     зап
    -0.06
     eder
    -0.06
     nộp
    -0.06
     teens
    -0.06
     gái
    -0.06
    POSITIVE LOGITS
    otions
    0.07
    ounced
    0.07
    .Lines
    0.07
     travelled
    0.07
     researched
    0.06
    -desc
    0.06
     stitch
    0.06
    Hz
    0.06
    urus
    0.06
     persona
    0.06
    Activations Density 0.191%

    No Known Activations