© 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. 128558
    Prev
    Next
    INDEX
    Explanations

    politicians from various countries

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of country names (e.g. “Japan,” “Mexico,” “Norway,” etc.), especially in category or parenthetical contexts.

    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
     convinc
    -0.08
     assistance
    -0.08
     Lazar
    -0.06
    Validity
    -0.06
    ==========
    -0.06
    eliminar
    -0.06
     lui
    -0.06
     Philipp
    -0.06
    Inform
    -0.06
     Positive
    -0.06
    POSITIVE LOGITS
    ?“↵↵
    0.07
    اضي
    0.06
     Differences
    0.06
    >List
    0.06
    embedded
    0.06
    �i
    0.06
     
    0.06
    牙
    0.06
    _Two
    0.06
    麦
    0.06
    Activations Density 0.005%

    No Known Activations