© 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. 56413
    Prev
    Next
    INDEX
    Explanations

    -based

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of population-based epidemiological study design terms (e.g., “population-based,” “prevalence,” “incidence”).

    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
    (as
    -0.07
    otate
    -0.06
    <Document
    -0.06
    _ex
    -0.06
    ADOW
    -0.06
     readability
    -0.06
     관심
    -0.06
     Solar
    -0.06
    '{
    -0.06
     использ
    -0.05
    POSITIVE LOGITS
    象
    0.07
     caregivers
    0.07
     字
    0.07
    roupon
    0.07
     gateway
    0.06
     inser
    0.06
     ๆ
    0.06
    rám
    0.06
     belonged
    0.06
     návrh
    0.06
    Activations Density 0.009%

    No Known Activations