© 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. 59144
    Prev
    Next
    INDEX
    Explanations

    prescribed

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of prescribing (or prescriptions of) medical treatments or medications.

    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
    Profit
    -0.07
     Johan
    -0.07
     Profit
    -0.07
     hrá
    -0.07
     robotics
    -0.07
    илася
    -0.07
    uni
    -0.07
    	logger
    -0.07
     laughter
    -0.07
    Activities
    -0.07
    POSITIVE LOGITS
     prescribed
    0.13
     prescription
    0.12
     prescribing
    0.11
     prescribe
    0.10
     Prescription
    0.09
     prescriptions
    0.09
    commercial
    0.07
     parch
    0.07
    icher
    0.07
    RX
    0.06
    Activations Density 0.005%

    No Known Activations