© 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. 6101
    Prev
    Next
    INDEX
    Explanations

    adherence to rules/laws

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases describing the implementation, enforcement, or flouting of rules and regulations.

    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
    рует
    -0.06
     handgun
    -0.06
    	byte
    -0.06
     示例
    -0.06
    developer
    -0.06
    ekil
    -0.06
    erialization
    -0.06
     installation
    -0.06
     дерева
    -0.06
     갤
    -0.06
    POSITIVE LOGITS
     onRequest
    0.07
     Flying
    0.07
     grö
    0.07
    "]->
    0.07
    $header
    0.06
     outros
    0.06
    .system
    0.06
     devoted
    0.06
     StringIO
    0.06
     mentioning
    0.06
    Activations Density 0.043%

    No Known Activations