© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128226
    Prev
    Next
    INDEX
    Explanations

    Code/Abbreviation

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the “NXP” prefix in technical tags (i.e., NXP-branded components or protocols).

    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
    	location
    -0.07
    ]){↵
    -0.07
     Surely
    -0.07
    ):
    ↵
    -0.06
     demand
    -0.06
     sv
    -0.06
     Demand
    -0.06
    +.
    -0.06
     movies
    -0.06
     Daddy
    -0.06
    POSITIVE LOGITS
     tbsp
    0.07
    源
    0.06
    ................................................................
    0.06
     масс
    0.05
    .getBody
    0.05
    %^
    0.05
     발
    0.05
    _passwd
    0.05
     přip
    0.05
    TargetException
    0.05
    Activations Density 0.122%

    No Known Activations