© 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. 126909
    Prev
    Next
    INDEX
    Explanations

    White House, president

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by words naming political offices, institutions, and high‐level government or electoral entities.

    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
    愿
    -0.07
    tak
    -0.07
    borne
    -0.06
    Asian
    -0.06
     broker
    -0.06
     sop
    -0.06
    CELL
    -0.06
     Brock
    -0.06
    sex
    -0.06
    for
    -0.06
    POSITIVE LOGITS
    ной
    0.07
    ernetes
    0.06
     ž
    0.06
    ナ
    0.06
    図
    0.06
    odář
    0.06
    ;↵↵↵
    0.06
     inorder
    0.06
     Bí
    0.06
    datum
    0.06
    Activations Density 0.039%

    No Known Activations