© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57959
    Prev
    Next
    INDEX
    Explanations

    duct

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of biliary anatomy, especially terms referring to bile ducts and related structures.

    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
    configuration
    -0.07
    )이
    -0.07
     study
    -0.07
     Xunit
    -0.07
    -return
    -0.07
    .calc
    -0.07
    Handle
    -0.06
    	On
    -0.06
    	Check
    -0.06
    Rule
    -0.06
    POSITIVE LOGITS
     endPoint
    0.06
     Snapdragon
    0.06
    cuador
    0.06
     Opens
    0.06
     monumental
    0.06
     fuzzy
    0.06
    .ObjectModel
    0.06
    ordable
    0.05
     Cre
    0.05
     Uzbek
    0.05
    Activations Density 0.022%

    No Known Activations