© 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. 101186
    Prev
    Next
    INDEX
    Explanations

    underscore

    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
     صح
    -0.07
     レ
    -0.07
    �
    -0.06
    КИ
    -0.06
     ين
    -0.06
    anson
    -0.06
    Lu
    -0.06
     Ст
    -0.06
    GTK
    -0.06
     学
    -0.06
    POSITIVE LOGITS
     bribery
    0.07
     ceasefire
    0.07
     आपक
    0.06
    anne
    0.06
    -transparent
    0.06
    じゃ
    0.06
    ニニニニ
    0.06
    -parser
    0.06
    σκευ
    0.06
     Gabriel
    0.06
    Activations Density 0.002%

    No Known Activations