© 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. 7177
    Prev
    Next
    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash

    pieces of code related to testing functionality in a programming context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the word “should” (as used in test-case descriptions).

    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
     Laurent
    -0.06
     nấu
    -0.06
    	TArray
    -0.06
     galleries
    -0.06
    AP
    -0.06
    	Item
    -0.06
     z
    -0.06
     salads
    -0.06
    ders
    -0.06
     Fare
    -0.06
    POSITIVE LOGITS
     ortaya
    0.07
    Bruce
    0.07
    currentPage
    0.06
    peaker
    0.06
    -txt
    0.06
    .Peek
    0.06
    Grace
    0.06
    _multiplier
    0.06
     Homeland
    0.06
    tabs
    0.06
    Activations Density 0.002%

    No Known Activations