© 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. 68328
    Prev
    Next
    INDEX
    Explanations

    production and ced

    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
     Corey
    -0.07
     Sey
    -0.07
     Stay
    -0.07
    _DBG
    -0.07
     '"+
    -0.07
     renovations
    -0.06
     WWW
    -0.06
     pied
    -0.06
     lazy
    -0.06
     freund
    -0.06
    POSITIVE LOGITS
     подготов
    0.07
    FL
    0.07
    _SEL
    0.07
    輯
    0.07
     آم
    0.07
    γκα
    0.07
    ประก
    0.07
    xl
    0.07
    	pl
    0.06
    ged
    0.06
    Activations Density 0.030%

    No Known Activations