© 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. 15-RESID-POST-AA
    6. 13660
    Prev
    Next
    INDEX
    Explanations

    Contractions and informal writing

    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
    …
    -0.06
     drone
    -0.06
     sampling
    -0.06
     Embed
    -0.06
    chemy
    -0.06
     purity
    -0.06
     lime
    -0.06
    -semibold
    -0.06
     hồng
    -0.06
     framed
    -0.06
    POSITIVE LOGITS
    acija
    0.07
    
    0.06
    ERRU
    0.06
    -properties
    0.06
    ducation
    0.06
     Flag
    0.06
    ічні
    0.06
    ова
    0.06
    WebResponse
    0.06
    cej
    0.06
    Activations Density 0.024%

    No Known Activations