© 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 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. 57209
    Prev
    Next
    INDEX
    Explanations

    nationalities

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of English or French national identifiers (e.g. “angl…,” “-aise,” “française,” “Édouard III”) in a military context.

    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
     Brom
    -0.07
    obierno
    -0.06
     Pin
    -0.06
     subscribe
    -0.06
    in
    -0.06
    бол
    -0.06
     вибор
    -0.06
    /wiki
    -0.06
    Removing
    -0.06
    _atual
    -0.06
    POSITIVE LOGITS
    /dd
    0.07
     ew
    0.07
    088
    0.06
    	first
    0.06
    087
    0.06
     Hive
    0.06
     result
    0.06
     lng
    0.06
    668
    0.06
     chod
    0.06
    Activations Density 0.015%

    No Known Activations