© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7019
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    The neuron detects promotional feature-highlighting language in real-estate listings (e.g. words introducing property amenities like “boasts,” “offers,” “with,” “featuring,” etc.).

    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
    しか
    -0.06
     ninth
    -0.06
    经过
    -0.06
    沉
    -0.06
     Citizen
    -0.06
    ('/')
    -0.06
     Guill
    -0.06
    arger
    -0.06
    lando
    -0.06
    POSITIVE LOGITS
     analogy
    0.06
    -HT
    0.06
    websocket
    0.06
     backpack
    0.06
    ilater
    0.06
     Vegetable
    0.06
     Veterinary
    0.06
    alted
    0.06
    discover
    0.06
    (pipe
    0.06
    Activations Density 0.010%

    No Known Activations