© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58918
    Prev
    Next
    INDEX
    Explanations

    article snippets

    np_max-act · gemini-2.0-flash

    This neuron responds to short sequences of uppercase letters, such as acronyms or organization abbreviations.

    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
     DataGridView
    -0.06
    .fromCharCode
    -0.06
    答案
    -0.06
     옥
    -0.06
     سرو
    -0.06
     Scheduler
    -0.06
     جزئ
    -0.06
     scaleFactor
    -0.06
     shepherd
    -0.06
    英文
    -0.06
    POSITIVE LOGITS
     fundraiser
    0.07
    .IM
    0.07
    least
    0.06
    >Contact
    0.06
     points
    0.06
    Image
    0.06
     posts
    0.06
     Innov
    0.06
    년
    0.06
     MLA
    0.06
    Activations Density 0.196%

    No Known Activations