© 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. 7022
    Prev
    Next
    INDEX
    Explanations

    Code or system configurations

    np_max-act · gemini-2.0-flash

    This neuron fires on identifiers for resource‐management actions (e.g. “create,” “edit,” “info,” “list,” etc.) in component or service definitions.

    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
    Points
    -0.07
    _Report
    -0.06
    _successful
    -0.06
    hive
    -0.06
    lems
    -0.06
    anda
    -0.06
    _Offset
    -0.06
    cen
    -0.06
    Handled
    -0.06
     사항
    -0.06
    POSITIVE LOGITS
     melod
    0.07
    [element
    0.06
     Academic
    0.06
     ทำให
    0.06
     aktuellen
    0.06
     strategist
    0.06
    tiği
    0.06
     USART
    0.06
    .assertTrue
    0.06
     üy
    0.06
    Activations Density 0.054%

    No Known Activations