© 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. 56237
    Prev
    Next
    INDEX
    Explanations

    Brands and video games

    np_max-act · gemini-2.0-flash

    The neuron activates strongly on proper names of technology products or brands (e.g. “Vue,” “Nvidia,” “AMD”), signaling detection of tech-related named entities.

    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
    329
    -0.08
    ×
    -0.07
    TP
    -0.07
     fled
    -0.06
    的话
    -0.06
    /graph
    -0.06
    auc
    -0.06
     Lower
    -0.06
    увала
    -0.06
     highest
    -0.06
    POSITIVE LOGITS
     канди
    0.07
    .XtraEditors
    0.07
     sexkontakte
    0.06
    .ColumnName
    0.06
     самов
    0.06
    块
    0.06
     stationed
    0.06
     Nasıl
    0.06
    .IsEnabled
    0.06
     torino
    0.06
    Activations Density 0.311%

    No Known Activations