© 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. 56389
    Prev
    Next
    INDEX
    Explanations

    Statistics and percentages

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of home technology adoption, especially phrases like “home computer” and “internet access.”

    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
     tourist
    -0.08
     negligence
    -0.06
    rection
    -0.06
     jewels
    -0.06
     handler
    -0.06
    urrency
    -0.06
     antioxidant
    -0.06
     frying
    -0.06
     Fond
    -0.06
     Leisure
    -0.06
    POSITIVE LOGITS
    mutation
    0.07
    .nanoTime
    0.07
    出售
    0.06
     rozdíl
    0.06
     olanak
    0.06
     permutation
    0.06
    |unique
    0.06
    .AC
    0.06
     Micha
    0.06
     عند
    0.06
    Activations Density 0.042%

    No Known Activations