© 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. 56209
    Prev
    Next
    INDEX
    Explanations

    -fat

    np_max-act · gemini-2.0-flash

    This neuron detects references to high-fat dietary conditions, specifically the “high-fat diet” phrase.

    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
     LAND
    -0.07
     oscill
    -0.06
     Warsaw
    -0.06
     BG
    -0.06
    だ
    -0.06
     Osw
    -0.06
    .book
    -0.06
     Gian
    -0.06
     sperm
    -0.06
     stern
    -0.06
    POSITIVE LOGITS
     taxpayers
    0.07
    .OrdinalIgnoreCase
    0.06
    爭
    0.06
    .
    ↵↵
    0.06
    <select
    0.06
    upply
    0.06
    ($__
    0.06
    .LogInformation
    0.06
    achment
    0.06
     contag
    0.06
    Activations Density 0.006%

    No Known Activations