© 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. 29615
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on the definite article “the,” as it appears in user questions (notably in the “What is the …?” phrase).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    questions related to mathematical concepts and operations, specifically focusing on square roots and their definitions.

    oai_token-act-pair · gpt-4o-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
    ">
↵
    -0.07
    FAIL
    -0.06
     Fransa
    -0.06
    ">&
    -0.06
     dati
    -0.06
     EINVAL
    -0.06
     �
    -0.06
     surroundings
    -0.06
    ="">
↵
    -0.06
     Joh
    -0.06
    POSITIVE LOGITS
    ционных
    0.07
     critiques
    0.07
     των
    0.06
    itty
    0.06
     frontal
    0.06
     Selector
    0.06
    nsic
    0.06
    ifikace
    0.06
    ût
    0.06
    LayoutPanel
    0.06
    Activations Density 0.008%

    No Known Activations