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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9029
    Prev
    Next
    INDEX
    Explanations

    Baptist

    np_max-act · gemini-2.0-flash

    This neuron activates on personal proper names (especially names of people, like saints or historical figures).

    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
    olg
    -0.08
    нив
    -0.07
     Hearts
    -0.06
     plaisir
    -0.06
     배
    -0.06
     иногда
    -0.06
     نیر
    -0.06
    pod
    -0.06
     дела
    -0.06
     neutrality
    -0.06
    POSITIVE LOGITS
    _mob
    0.07
    compress
    0.07
    /gui
    0.06
    Official
    0.06
    ']));
    0.06
    ある
    0.06
    Item
    0.06
    	fwrite
    0.06
        	   
    0.06
    accessible
    0.06
    Activations Density 0.003%

    No Known Activations