© 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. 74016
    Prev
    Next
    INDEX
    Explanations

    towns and regions

    np_max-act · gemini-2.0-flash

    The neuron fires on passages that define or describe an administrative entity—e.g. “The commune/municipality is…” or “It is composed of…” statements about a place’s administrative status or composition.

    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
    723
    -0.07
     neut
    -0.06
    opping
    -0.06
    ownership
    -0.06
    ‌ش
    -0.06
    Addr
    -0.06
    bubble
    -0.06
     Yah
    -0.06
     WAL
    -0.06
     segment
    -0.06
    POSITIVE LOGITS
     mulher
    0.07
    firstName
    0.07
    "))))↵
    0.06
    	printk
    0.06
     řid
    0.06
    :"↵
    0.06
    ',...↵
    0.06
    ,param
    0.06
    .getRequestDispatcher
    0.06
     femme
    0.06
    Activations Density 0.011%

    No Known Activations