© 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. 23111
    Prev
    Next
    INDEX
    Explanations

    relationships

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of people — tokens that indicate personal names or references to individuals/relationships.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     fw
    -0.07
     pj
    -0.06
    流
    -0.06
     бенз
    -0.06
     fmap
    -0.06
     trains
    -0.06
    �
    -0.06
    .row
    -0.06
     �
    -0.06
    مان
    -0.06
    POSITIVE LOGITS
    inement
    0.07
     pathname
    0.06
     dern
    0.06
     เมตร
    0.06
     guidance
    0.06
    .mp
    0.06
    BarItem
    0.06
    :function
    0.06
    /sources
    0.06
    .DropDownStyle
    0.06
    Activations Density 0.175%

    No Known Activations