© 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. 104196
    Prev
    Next
    INDEX
    Explanations

    .application

    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
     fare
    -0.07
     stat
    -0.06
     köln
    -0.06
    lož
    -0.06
     juris
    -0.06
     치
    -0.06
     Wimbledon
    -0.06
    _pas
    -0.06
    健康
    -0.06
     земель
    -0.05
    POSITIVE LOGITS
     until
    0.07
     Jazeera
    0.07
     große
    0.07
    prevent
    0.07
    /ml
    0.06
     //*
    0.06
    /game
    0.06
    intendo
    0.06
    SqlServer
    0.06
     Delay
    0.06
    Activations Density 0.001%

    No Known Activations