© 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. 9514
    Prev
    Next
    INDEX
    Explanations

    images

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases referring to high-quality visual content (e.g. images, visuals, design/appeal).

    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
     evangel
    -0.07
     entrepreneurship
    -0.07
    IGNAL
    -0.07
    薄
    -0.06
     Ezra
    -0.06
     Ru
    -0.06
     Antarctica
    -0.06
     Alert
    -0.06
    ku
    -0.06
    signal
    -0.06
    POSITIVE LOGITS
    embed
    0.07
     pics
    0.07
     فلس
    0.06
    قية
    0.06
     \(
    0.06
     aperture
    0.06
    \(
    0.06
    ीफ
    0.06
     Plate
    0.06
    immers
    0.06
    Activations Density 0.019%

    No Known Activations