© 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. 7218
    Prev
    Next
    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of government bodies or official state institutions (especially in Portuguese).

    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
    르
    -0.07
     친구
    -0.06
    \Foundation
    -0.06
     introductory
    -0.06
     generally
    -0.06
    퓨터
    -0.06
     Maintenance
    -0.06
    性能
    -0.06
    愿
    -0.06
     Algorithms
    -0.06
    POSITIVE LOGITS
     BDSM
    0.07
    633
    0.07
     MGM
    0.06
     AVC
    0.06
    HR
    0.06
    	IL
    0.06
    vida
    0.06
     staring
    0.06
    WORK
    0.06
    !",↵
    0.06
    Activations Density 0.025%

    No Known Activations