© 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. 30631
    Prev
    Next
    INDEX
    Explanations

    何

    np_max-act · gemini-2.0-flash

    The neuron is detecting the Korean question word “뭐” (as in casual “뭐야?”) in user queries.

    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
    رك
    -0.07
    laces
    -0.06
     }}>
    -0.06
    oplast
    -0.06
    chers
    -0.06
    нит
    -0.06
    осков
    -0.06
    agnetic
    -0.06
    Torrent
    -0.06
     nhạc
    -0.06
    POSITIVE LOGITS
     뭐
    0.08
    、何
    0.07
    .getRequest
    0.06
     reunion
    0.06
    무
    0.06
     moo
    0.06
    ((_
    0.06
     �
    0.06
     stiff
    0.06
     И
    0.06
    Activations Density 0.002%

    No Known Activations