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

    Neuronpedia

    APICircuit 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. 130339
    Prev
    Next
    INDEX
    Explanations

    Puerto

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of Puerto Rico and related place names (e.g., “Puerto Rico,” “San Juan,” “Carolina”).

    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
    osl
    -0.06
    similar
    -0.06
     Stevenson
    -0.06
    坐在
    -0.06
     Medium
    -0.06
    655
    -0.06
    ANEL
    -0.06
    l
    -0.06
    616
    -0.06
    floor
    -0.06
    POSITIVE LOGITS
     Puerto
    0.10
     Rico
    0.09
    .remote
    0.07
    oubtedly
    0.07
     imu
    0.07
     Guam
    0.07
     Homeland
    0.07
    ikat
    0.07
    erved
    0.06
     crochet
    0.06
    Activations Density 0.003%

    No Known Activations