© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44541
    Prev
    Next
    INDEX
    Explanations

    international

    np_max-act · gemini-2.0-flash

    The neuron detects multiword proper‐noun nicknames (often of sports teams or places), such as “La Albiceleste,” “Men in Green,” “Beehive State,” or “Les Bleus.”

    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
    session
    -0.06
    inality
    -0.06
     Diamonds
    -0.06
    那里
    -0.06
    Atl
    -0.06
     sovere
    -0.06
     �
    -0.06
    _CTL
    -0.06
    Gran
    -0.06
     Kö
    -0.06
    POSITIVE LOGITS
    .message
    0.07
     WARRANTIES
    0.07
    Them
    0.07
     altern
    0.06
     أبريل
    0.06
    (save
    0.06
    оч
    0.06
    StepThrough
    0.06
    超过
    0.06
    CLAIM
    0.06
    Activations Density 0.026%

    No Known Activations