© 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
    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. 6365
    Prev
    Next
    INDEX
    Explanations

    republic

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of China’s official names and related acronyms (e.g. “People’s Republic,” “PRC,” “RMB”).

    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
    appointed
    -0.07
     Ric
    -0.07
    چه
    -0.07
     unsur
    -0.07
     Mae
    -0.06
    ByteBuffer
    -0.06
    柜
    -0.06
     подав
    -0.06
     circuit
    -0.06
     caul
    -0.06
    POSITIVE LOGITS
     ForCanBeConvertedToF
    0.07
     repetitions
    0.06
     items
    0.06
    .GetSize
    0.06
     μικ
    0.06
    _PRODUCT
    0.06
     imgs
    0.06
    riteln
    0.06
    "]==
    0.06
     production
    0.06
    Activations Density 0.009%

    No Known Activations