© 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. 11-RESID-POST-AA
    6. 65327
    Prev
    Next
    INDEX
    Explanations

    Data and technical language

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     span
    -0.06
    PARSE
    -0.06
     calibrated
    -0.06
    itted
    -0.06
    /engine
    -0.06
     кан
    -0.06
     lion
    -0.06
    字幕
    -0.06
    	direction
    -0.06
    τρα
    -0.06
    POSITIVE LOGITS
     Ziel
    0.07
     pokoj
    0.07
    _RESULTS
    0.07
     México
    0.06
     Personen
    0.06
     Raum
    0.06
    <Class
    0.06
     diệt
    0.06
    _attempt
    0.06
     Ein
    0.06
    Activations Density 0.215%

    No Known Activations