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

    Neuronpedia

    Jacobian LensNEW
    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. 38914
    Prev
    Next
    INDEX
    Explanations

    Japanese language

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on polite “offer to help” phrases in Japanese and Korean (e.g. “何かお手伝いできますか？” or “도와드릴까요?”).

    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
     lact
    -0.07
    	stmt
    -0.06
     Furn
    -0.06
     незалеж
    -0.06
     prevention
    -0.06
     Sharing
    -0.06
     apopt
    -0.06
     Basin
    -0.06
     acrylic
    -0.06
     здоров
    -0.06
    POSITIVE LOGITS
    (bot
    0.07
     ／
    0.07
     systemctl
    0.06
    },'
    0.06
    pn
    0.06
     iterations
    0.06
    Searching
    0.06
    sendMessage
    0.06
    xea
    0.06
    nom
    0.06
    Activations Density 0.007%

    No Known Activations