© 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. 130003
    Prev
    Next
    INDEX
    Explanations

    real estate for entertaining

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of specific rooms, features, or amenity spaces (e.g. family room, snack counter, craft area) in a real‐estate listing.

    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
     Lines
    -0.07
    rok
    -0.07
     Lol
    -0.06
     прок
    -0.06
     Louis
    -0.06
     Damon
    -0.06
    owe
    -0.06
     Immigration
    -0.06
     Liga
    -0.06
     frail
    -0.06
    POSITIVE LOGITS
    _estado
    0.07
    ечение
    0.07
    venile
    0.07
     DirectoryInfo
    0.06
     Ελλάδα
    0.06
     Між
    0.06
    谢
    0.06
     โรง
    0.06
    SU
    0.06
    marginLeft
    0.06
    Activations Density 0.009%

    No Known Activations