© 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. 54573
    Prev
    Next
    INDEX
    Explanations

    fatigue

    np_max-act · gemini-2.0-flash

    medical terminology and phrases related to chronic health conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron strongly responds to mentions of chronic fatigue syndrome (and its related terms like “fatigue,” “syndrome,” “ME,” “CFS,” etc.).

    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
     Math
    -0.08
    ั
    -0.07
     мире
    -0.07
     takový
    -0.06
     الإسلام
    -0.06
     помощ
    -0.06
    主任
    -0.06
     ast
    -0.06
    лой
    -0.06
     hakkı
    -0.06
    POSITIVE LOGITS
    latesAutoresizingMaskIntoConstraints
    0.07
     Firearms
    0.06
     dedi
    0.06
    ometown
    0.06
     conseguir
    0.06
     Erica
    0.06
    rene
    0.06
     commerc
    0.06
    .fontSize
    0.06
    eatures
    0.06
    Activations Density 0.001%

    No Known Activations