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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84370
    Prev
    Next
    INDEX
    Explanations

    USA locations

    np_max-act · gemini-2.0-flash

    The neuron detects capitalized named entities—particularly organization names and geographic locations.

    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
     могу
    -0.07
    .try
    -0.07
    .screen
    -0.06
     Injector
    -0.06
     injector
    -0.06
     '</
    -0.06
     Cao
    -0.06
     представ
    -0.06
     tion
    -0.06
    サービス
    -0.06
    POSITIVE LOGITS
     ㅇ
    0.07
    жно
    0.07
    产生
    0.06
    throws
    0.06
     christ
    0.06
     Lum
    0.06
    ****************
    0.06
    акс
    0.06
    _decor
    0.06
    �
    0.06
    Activations Density 0.103%

    No Known Activations