© 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. 9344
    Prev
    Next
    INDEX
    Explanations

    image AI

    np_max-act · gemini-2.0-flash

    The neuron fires on the descriptive “capability” language used when introducing or characterizing AI image‐generation models (e.g. “StyleGAN is an advanced generative adversarial network … capable of generating high‐resolution, photorealistic images in various styles”).

    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
    	username
    -0.07
     dragon
    -0.07
    LocalizedMessage
    -0.06
    Hz
    -0.06
     hedge
    -0.06
    "k
    -0.06
    .are
    -0.06
     подход
    -0.06
    ocabulary
    -0.06
     dragons
    -0.06
    POSITIVE LOGITS
    bote
    0.07
    prepare
    0.06
    异
    0.06
    剛
    0.06
    obre
    0.06
     Yep
    0.06
     rounded
    0.06
    trail
    0.06
     Ninh
    0.06
    Při
    0.06
    Activations Density 0.030%

    No Known Activations