© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91568
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of artificial intelligence (e.g. terms like “artificiale,” “intelligenza,” and related AI references).

    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
    텔
    -0.07
    	read
    -0.07
     Doug
    -0.06
     adher
    -0.06
    network
    -0.06
     pioneering
    -0.06
    Doug
    -0.06
     docking
    -0.06
     dad
    -0.06
     donors
    -0.06
    POSITIVE LOGITS
    .r
    0.08
     виготов
    0.07
    кость
    0.07
     Geo
    0.07
    >No
    0.07
    *y
    0.07
     ST
    0.07
    eza
    0.07
    InSeconds
    0.07
    Geo
    0.07
    Activations Density 0.010%

    No Known Activations