© 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. 8965
    Prev
    Next
    INDEX
    Explanations

    pragmatic

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on occurrences of the word “pragmatic” (and its morphological fragments).

    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
    	clock
    -0.07
     Walk
    -0.07
     место
    -0.07
    ителей
    -0.07
    _main
    -0.06
    报告
    -0.06
     Hollow
    -0.06
     contributor
    -0.06
     resistance
    -0.06
    386
    -0.06
    POSITIVE LOGITS
     pragmatic
    0.09
     prag
    0.07
    .Linq
    0.06
     Neo
    0.06
     formulate
    0.06
    needs
    0.06
    んと
    0.06
    ?action
    0.06
    Sometimes
    0.06
    _flashdata
    0.06
    Activations Density 0.002%

    No Known Activations