© 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. 128235
    Prev
    Next
    INDEX
    Explanations

    pharmaceuticals and medical treatments

    np_max-act · gemini-2.0-flash

    This neuron responds to terminology related to pharmaceuticals and drug development (e.g., mentions of drugs, treatments, approvals, patients, and related industry/value concepts).

    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
    817
    -0.06
     inputs
    -0.06
     Passed
    -0.06
     Ed
    -0.06
    .photo
    -0.06
    AccessToken
    -0.06
    소를
    -0.06
     Aim
    -0.06
     relocation
    -0.06
    (speed
    -0.06
    POSITIVE LOGITS
     Kavanaugh
    0.08
    ,《
    0.07
     sociální
    0.07
     मस
    0.07
     пласти
    0.06
     contentView
    0.06
     пон
    0.06
    ottesville
    0.06
     начинает
    0.06
    _all
    0.06
    Activations Density 0.023%

    No Known Activations