© 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. 12382
    Prev
    Next
    INDEX
    Explanations

    shutdown

    np_max-act · gemini-2.0-flash

    The neuron fires on words related to shutting down or powering down (e.g. “down,” “shutdown,” “shutting”).

    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
     detects
    -0.07
    یم
    -0.06
    �제
    -0.06
     Ella
    -0.06
     contenders
    -0.06
     Relative
    -0.06
     EIF
    -0.06
     returns
    -0.06
     engages
    -0.06
     Rect
    -0.06
    POSITIVE LOGITS
     shutdown
    0.12
    shutdown
    0.09
    Shutdown
    0.08
    .shutdown
    0.08
     navCtrl
    0.07
    china
    0.07
     Shutdown
    0.07
    utdown
    0.07
     Goldman
    0.07
     closure
    0.07
    Activations Density 0.003%

    No Known Activations