© 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. 55905
    Prev
    Next
    INDEX
    Explanations

    to

    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
    illisecond
    -0.07
    Tel
    -0.06
     mga
    -0.06
    sam
    -0.06
    όν
    -0.06
    ферен
    -0.06
    ei
    -0.06
     jr
    -0.06
     journals
    -0.06
    нем
    -0.06
    POSITIVE LOGITS
    ा↵↵
    0.07
    Window
    0.07
    δες
    0.06
    憶
    0.06
    浦
    0.06
     aunque
    0.06
    Correo
    0.06
    Motion
    0.06
    恶
    0.06
     Day
    0.06
    Activations Density 0.000%

    No Known Activations