© 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. 30617
    Prev
    Next
    INDEX
    Explanations

    Europe

    np_max-act · gemini-2.0-flash

    The neuron activates on references to “Europe” (and closely related terms like European or Europeans).

    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
     tempfile
    -0.07
     inspection
    -0.06
     findings
    -0.06
    .mid
    -0.06
     assaults
    -0.06
     title
    -0.06
     recalls
    -0.06
     Patrol
    -0.06
     validity
    -0.06
    innie
    -0.06
    POSITIVE LOGITS
     European
    0.18
     Europe
    0.16
    European
    0.14
    -European
    0.11
     欧
    0.10
    欧
    0.09
     Avrupa
    0.09
     european
    0.09
     Europeans
    0.09
     EU
    0.09
    Activations Density 0.017%

    No Known Activations