© 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. 8676
    Prev
    Next
    INDEX
    Explanations

    A

    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
    GORITH
    -0.07
    亭
    -0.07
    んと
    -0.07
    ainties
    -0.07
    ĞI
    -0.06
    ΥΝ
    -0.06
     �
    -0.06
    الح
    -0.06
     Roths
    -0.06
    λεύ
    -0.06
    POSITIVE LOGITS
     застосов
    0.07
    Sort
    0.07
     operators
    0.07
     Som
    0.06
     vielleicht
    0.06
     modifier
    0.06
     plugins
    0.06
    ksen
    0.06
     Excel
    0.06
    label
    0.06
    Activations Density 0.000%

    No Known Activations