© 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. 44559
    Prev
    Next
    INDEX
    Explanations

    groups

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of a collective group (e.g. “team,” “crew”) when describing ensemble casts or teams of characters.

    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
    dock
    -0.06
    论文
    -0.06
    от
    -0.06
     dread
    -0.06
    ("**
    -0.06
    Container
    -0.06
     catapult
    -0.06
     />,
    -0.06
    Password
    -0.06
    lass
    -0.06
    POSITIVE LOGITS
     lub
    0.07
    COPE
    0.07
     roster
    0.07
     ensued
    0.06
     Thành
    0.06
    valuator
    0.06
     suprem
    0.06
     realiza
    0.06
     reorder
    0.06
    .ResponseWriter
    0.06
    Activations Density 0.071%

    No Known Activations