© 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. 7441
    Prev
    Next
    INDEX
    Explanations

    esModule

    np_max-act · gemini-2.0-flash

    This neuron detects the `__esModule` property flag used in transpiled/module boilerplate.

    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
    테
    -0.07
    tığı
    -0.06
    }/>
    -0.06
     }}/
    -0.06
    '}).
    -0.06
    	range
    -0.06
    ")}
    -0.06
    ']}'
    -0.06
     }\
    -0.06
    })"↵
    -0.06
    POSITIVE LOGITS
    esModule
    0.09
    agra
    0.07
     scientifically
    0.07
    .orders
    0.07
    scr
    0.06
    EU
    0.06
     如
    0.06
    adj
    0.06
    wcsstore
    0.06
     ecosystem
    0.06
    Activations Density 0.000%

    No Known Activations