© 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. 125192
    Prev
    Next
    INDEX
    Explanations

    writing/communication

    np_max-act · gemini-2.0-flash

    This neuron activates on second-person imperative and directive verbs—i.e., user instructions like “Go,” “Follow,” or “Use.”

    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
    rying
    -0.06
    rated
    -0.06
    ่วน
    -0.06
     punched
    -0.06
     працівників
    -0.06
    embro
    -0.06
    —including
    -0.06
     Petro
    -0.06
    aramel
    -0.06
    edula
    -0.06
    POSITIVE LOGITS
     inconsistent
    0.06
     rice
    0.06
     sweater
    0.06
     reply
    0.06
     Cloth
    0.06
    (["
    0.06
     asynchronously
    0.06
     کاهش
    0.06
     JMP
    0.06
    ventory
    0.06
    Activations Density 0.058%

    No Known Activations