© 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. 68324
    Prev
    Next
    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash

    The neuron activates on personal names (and related references) in biographical text.

    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
     names
    -0.07
     Witnesses
    -0.07
     witnesses
    -0.06
     Model
    -0.06
     geometric
    -0.06
    하면서
    -0.06
    779
    -0.06
    یین
    -0.06
     Trident
    -0.06
     Beer
    -0.06
    POSITIVE LOGITS
    .food
    0.06
    iteur
    0.06
    ---↵
    0.06
    ングル
    0.06
    administrator
    0.06
    "log
    0.06
    -floating
    0.06
    ("("
    0.06
     dahi
    0.06
    wayne
    0.06
    Activations Density 0.053%

    No Known Activations