© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110455
    Prev
    Next
    INDEX
    Explanations

    simulation

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of simulation technology or simulator-based training (e.g. “simulation,” “sim,” “simulator,” “simulation-based,” etc.).

    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
    Positive
    -0.07
     olds
    -0.07
     گ
    -0.06
     Hearts
    -0.06
     فضای
    -0.06
     �
    -0.06
    甚
    -0.06
     �
    -0.06
     Hundred
    -0.06
     Friendly
    -0.06
    POSITIVE LOGITS
    امة
    0.07
    (full
    0.07
    MenuItem
    0.07
     atual
    0.07
    enqueue
    0.06
    (layers
    0.06
     enclave
    0.06
    ociety
    0.06
     Throw
    0.06
    volution
    0.06
    Activations Density 0.014%

    No Known Activations