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

    Neuronpedia

    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. 68316
    Prev
    Next
    INDEX
    Explanations

    synthesis

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on the word “production” (and related “production process”) in the text.

    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
    871
    -0.06
     payloads
    -0.06
    .height
    -0.06
     chose
    -0.06
     wand
    -0.06
    eddar
    -0.06
    _scr
    -0.06
    -cluster
    -0.06
    FileSize
    -0.06
    _Input
    -0.06
    POSITIVE LOGITS
     пер
    0.08
     Phân
    0.07
     ┃
    0.07
     uLocal
    0.07
    없는
    0.07
    ��
    0.06
    ENE
    0.06
     Huyện
    0.06
     inflater
    0.06
    tab
    0.06
    Activations Density 0.023%

    No Known Activations