© 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. 89490
    Prev
    Next
    INDEX
    Explanations

    inc

    np_max-act · gemini-2.0-flash

    The neuron is keyed to the “inc” substring—i.e. it fires on the “inc” in words like “incorporated” (especially “unincorporated”).

    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
    ‌‌
    -0.07
    cores
    -0.06
     correctly
    -0.06
    언
    -0.06
    IMUM
    -0.06
    _sidebar
    -0.05
    /Login
    -0.05
    SWG
    -0.05
    Regressor
    -0.05
     εκεί
    -0.05
    POSITIVE LOGITS
     comparer
    0.07
     sweaty
    0.07
     sequelize
    0.07
     abrasive
    0.07
     ди
    0.07
     Cartesian
    0.07
    prene
    0.06
    яб
    0.06
        					
    0.06
     TSA
    0.06
    Activations Density 0.015%

    No Known Activations