© 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. 101166
    Prev
    Next
    INDEX
    Explanations

    :

    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
     standout
    -0.07
     least
    -0.07
     NSLog
    -0.07
     notable
    -0.06
     societies
    -0.06
     Mart
    -0.06
    animate
    -0.06
     Л
    -0.06
     sho
    -0.06
    —I
    -0.06
    POSITIVE LOGITS
     vide
    0.07
    ィ
    0.07
    rypton
    0.07
     连
    0.06
    ング
    0.06
     cerv
    0.06
    'nda
    0.06
    ↵↵↵
    0.06
    
    0.06
     nud
    0.06
    Activations Density 0.003%

    No Known Activations