© 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. 39143
    Prev
    Next
    INDEX
    Explanations

    image generation

    np_max-act · gemini-2.0-flash

    The neuron activates on references to AI image‐generation (text‐to‐image) tools and related terms (e.g. “-to-image,” “Midjourney,” “Stable Diffusion,” “generate,” “image”).

    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
    .nextInt
    -0.06
    ected
    -0.06
    ibe
    -0.06
     gdk
    -0.06
     větší
    -0.06
     打
    -0.06
    omu
    -0.06
    ReadOnly
    -0.06
     GBP
    -0.06
     tem
    -0.06
    POSITIVE LOGITS
     پیش
    0.07
    ridge
    0.07
     delim
    0.07
     Beacon
    0.07
    blast
    0.07
    포
    0.06
     приз
    0.06
     Amanda
    0.06
     connexion
    0.06
     squirt
    0.06
    Activations Density 0.012%

    No Known Activations