© 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. 15-RESID-POST-AA
    11. 107196
    Prev
    Next
    INDEX
    Explanations

    loyal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	store
    -0.07
    	Print
    -0.07
     chụp
    -0.07
    Ģ
    -0.07
    ยวก
    -0.06
    _heads
    -0.06
    mnop
    -0.06
     crackers
    -0.06
    baseline
    -0.06
     miner
    -0.06
    POSITIVE LOGITS
     loyal
    0.12
     loyalty
    0.09
    (es
    0.07
     faithful
    0.07
    \Exceptions
    0.06
     devotion
    0.06
    VALUE
    0.06
     فصل
    0.06
     fidelity
    0.06
     Στο
    0.06
    Activations Density 0.013%

    No Known Activations