© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30653
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    The neuron responds to geographical location names (countries, cities, regions, and related proper-noun place terms).

    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
    Wolf
    -0.07
     прит
    -0.07
     femmes
    -0.07
    993
    -0.07
    Privacy
    -0.07
    湖
    -0.06
    ategor
    -0.06
    WK
    -0.06
    Roll
    -0.06
     GIS
    -0.06
    POSITIVE LOGITS
     наличи
    0.07
     #%
    0.06
     Lon
    0.06
     onMouse
    0.06
    .onStart
    0.06
     />}↵
    0.06
     Munich
    0.06
    <Transaction
    0.06
     #:
    0.06
     iface
    0.06
    Activations Density 0.045%

    No Known Activations