© 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
    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. 89090
    Prev
    Next
    INDEX
    Explanations

    names, places

    np_max-act · gemini-2.0-flash

    The neuron fires on the very first multi-token name at the top of each entry—that is, the romanized title or proper name heading of a Wikipedia article.

    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
    (Function
    -0.07
     смеш
    -0.06
    >We
    -0.06
    Physics
    -0.06
    Good
    -0.06
    ريب
    -0.06
     آلمان
    -0.06
     Technical
    -0.06
     technical
    -0.06
    良
    -0.06
    POSITIVE LOGITS
     resizing
    0.06
    odu
    0.06
    ुट
    0.06
     thankful
    0.06
    Province
    0.06
    ention
    0.06
     získ
    0.06
     엄마
    0.06
    iever
    0.06
     Sil
    0.06
    Activations Density 0.031%

    No Known Activations