© 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. 68459
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the definite article “the.”

    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
     Gab
    -0.08
     interpretation
    -0.08
     ListItem
    -0.07
     Eventually
    -0.07
    Interpreter
    -0.07
    APPLICATION
    -0.06
     Picker
    -0.06
     Thực
    -0.06
    Integration
    -0.06
    ста
    -0.06
    POSITIVE LOGITS
     Scores
    0.06
    ์ท
    0.06
    .TestCheck
    0.06
    .setId
    0.06
    _CART
    0.06
     newsp
    0.06
     респ
    0.05
    ังส
    0.05
    \Order
    0.05
     počet
    0.05
    Activations Density 0.033%

    No Known Activations