Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27166
    Prev
    Next
    INDEX
    Explanations

    Slavic/Eastern European

    np_max-act · gemini-2.0-flash

    This neuron detects nationality or ethnic descriptors (demonyms) in text.

    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
    य
    -0.06
    ーフ
    -0.06
    ิถ
    -0.06
    esse
    -0.06
     world
    -0.06
     QStringLiteral
    -0.06
     Subway
    -0.06
    DataService
    -0.06
    泰
    -0.06
     Hurt
    -0.06
    POSITIVE LOGITS
     Result
    0.07
     Proposition
    0.07
    ulan
    0.07
     Derrick
    0.06
    mps
    0.06
     Remark
    0.06
     pruning
    0.06
    Dep
    0.06
     midfield
    0.06
    icture
    0.06
    Activations Density 0.024%

    No Known Activations