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. 8155
    Prev
    Next
    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of Korean personal names accompanied by official titles (e.g. “백군기 용인시장”).

    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
    Daniel
    -0.07
     퍼
    -0.06
    Value
    -0.06
     建
    -0.06
    руш
    -0.06
    kud
    -0.06
     RegexOptions
    -0.06
     Poh
    -0.06
     Γου
    -0.06
     använd
    -0.06
    POSITIVE LOGITS
    -spot
    0.06
    highest
    0.06
     @
    0.06
    개월
    0.06
     ώρα
    0.06
    祝
    0.06
    看看
    0.06
    .logical
    0.06
     웹
    0.06
    _force
    0.06
    Activations Density 0.011%

    No Known Activations