© 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
    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. 42784
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a company’s headquarters or primary location (e.g., “headquartered in Irving, Texas,” “based in Paris, France”).

    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
    _rules
    -0.08
    臣
    -0.07
    یان
    -0.07
    831
    -0.07
    /messages
    -0.07
    plug
    -0.07
    _Color
    -0.06
    琴
    -0.06
     legs
    -0.06
     courageous
    -0.06
    POSITIVE LOGITS
    NYSE
    0.06
     STDOUT
    0.06
    	p
    0.06
     Westminster
    0.06
    ++;
↵
    0.06
    İş
    0.06
     فس
    0.06
    urls
    0.06
    .tim
    0.05
     SMTP
    0.05
    Activations Density 0.017%

    No Known Activations