© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 627
    Prev
    Next
    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on the capitalized definite article “The,” especially when it begins a new sentence or section.

    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
    52
    -0.07
    51
    -0.07
    63
    -0.07
    618
    -0.06
    50
    -0.06
    551
    -0.06
    602
    -0.06
    2
    -0.06
    41
    -0.06
    31
    -0.06
    POSITIVE LOGITS
    The
    0.11
     The
    0.10
     біля
    0.08
    。<
    0.08
     dve
    0.08
    ्‍
    0.07
    -The
    0.07
    Tên
    0.07
     bulunduğu
    0.07
     grounded
    0.07
    Activations Density 0.229%

    No Known Activations