© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126074
    Prev
    Next
    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash

    The neuron detects words that name or label geographic or administrative entities (e.g. “Avenue,” “Regency,” “Province,” “Street”).

    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
    allery
    -0.07
     �
    -0.07
     hefty
    -0.07
     GOODMAN
    -0.06
    黒
    -0.06
    ्य
    -0.06
    呼
    -0.06
    iên
    -0.06
     Male
    -0.06
     nerv
    -0.06
    POSITIVE LOGITS
     ez
    0.07
    -session
    0.07
     기반
    0.07
    UU
    0.06
     všechno
    0.06
     onComplete
    0.06
    larınız
    0.06
     Türkiye
    0.06
     gö
    0.06
    Extend
    0.06
    Activations Density 0.168%

    No Known Activations