© 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. 130018
    Prev
    Next
    INDEX
    Explanations

    technology, products, news

    np_max-act · gemini-2.0-flash

    This neuron activates on multi-letter capitalized product or protocol names and acronyms.

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

    named entities such as organization/product names, acronyms, and other proper nouns.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    [port
    -0.06
     Flags
    -0.06
    hesive
    -0.06
    _tickets
    -0.06
    addons
    -0.06
     syntax
    -0.06
     TEST
    -0.06
     sadly
    -0.06
     opcode
    -0.06
    ancement
    -0.06
    POSITIVE LOGITS
    踏
    0.07
     practition
    0.07
    併
    0.07
     Maced
    0.07
     Би
    0.06
    	IN
    0.06
    =Math
    0.06
     해당
    0.06
    NewLabel
    0.06
     이동합니다
    0.06
    Activations Density 0.357%

    No Known Activations