Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130783
    Prev
    Next
    INDEX
    Explanations

    medical research

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the drug name “dexamethasone.”

    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
    HIR
    -0.06
     CI
    -0.06
    Birth
    -0.06
    Oil
    -0.06
    لف
    -0.06
     Rub
    -0.06
    혀
    -0.06
    .Car
    -0.05
     Fruit
    -0.05
    (Card
    -0.05
    POSITIVE LOGITS
    SON
    0.08
    son
    0.08
     disse
    0.07
     uncon
    0.07
     základní
    0.07
     locationManager
    0.07
     thoại
    0.07
    Anyone
    0.07
    pose
    0.07
     ώρα
    0.07
    Activations Density 0.002%

    No Known Activations