© 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. 29802
    Prev
    Next
    INDEX
    Explanations

    Political leaders/rulers

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of political leaders—especially dictators or presidents—along with verbs and details describing their rule or tenure.

    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
     Memories
    -0.07
     envelopes
    -0.07
    .lists
    -0.07
     gun
    -0.06
    .social
    -0.06
    uxe
    -0.06
    -wheel
    -0.06
    .Memory
    -0.06
     commons
    -0.06
    _evt
    -0.06
    POSITIVE LOGITS
     сохра
    0.06
    ossip
    0.06
    (found
    0.06
    :Boolean
    0.06
    Quite
    0.06
     sku
    0.06
    ms
    0.06
     Conexion
    0.06
     عفش
    0.06
    ़त
    0.06
    Activations Density 0.035%

    No Known Activations