© 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. 56244
    Prev
    Next
    INDEX
    Explanations

    Osama bin Laden

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “Osama bin Laden.”

    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
     Truck
    -0.07
     backtrack
    -0.06
    .over
    -0.06
     Rue
    -0.06
    			        
    -0.06
     undermined
    -0.06
     IEEE
    -0.06
     Tran
    -0.06
     NRF
    -0.06
     par
    -0.06
    POSITIVE LOGITS
    664
    0.07
    lexical
    0.06
     Üy
    0.06
     çıkan
    0.06
    рол
    0.06
    važ
    0.06
    ęk
    0.06
     khách
    0.06
    omanip
    0.06
    通知
    0.06
    Activations Density 0.005%

    No Known Activations