© 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. 3-RESID-POST-AA
    11. 93741
    Prev
    Next
    INDEX
    Explanations

    els

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retirees
    -0.07
    ires
    -0.06
    	con
    -0.06
     satisf
    -0.06
    enou
    -0.06
    Mine
    -0.06
    نتاج
    -0.06
     dị
    -0.06
     타이
    -0.06
    *i
    -0.06
    POSITIVE LOGITS
     propelled
    0.21
     propel
    0.20
     propulsion
    0.13
     Propel
    0.13
    履
    0.09
    виг
    0.07
    燃
    0.07
    姓名
    0.07
     улыб
    0.07
    護
    0.07
    Activations Density 0.008%

    No Known Activations