© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109743
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron fires on the instruction prompt telling the assistant to “Start with Yes or No.”

    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
     Guru
    -0.06
    δες
    -0.06
    Hide
    -0.06
    .Remove
    -0.06
    viewer
    -0.06
    arians
    -0.06
     ฟ
    -0.06
    盛
    -0.06
     eased
    -0.05
     важно
    -0.05
    POSITIVE LOGITS
     Electron
    0.06
    chs
    0.06
     golden
    0.06
     ]↵
    0.06
     California
    0.06
    TestMethod
    0.06
    -string
    0.06
     生命周期函数
    0.06
     string
    0.06
     electron
    0.06
    Activations Density 0.001%

    No Known Activations