© 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. 23080
    Prev
    Next
    INDEX
    Explanations

    Public

    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
    包括
    -0.07
    	rows
    -0.06
    	all
    -0.06
    	model
    -0.06
    machine
    -0.06
     pensions
    -0.06
     writable
    -0.06
    	b
    -0.06
     sollten
    -0.06
     Leonard
    -0.06
    POSITIVE LOGITS
     Revised
    0.07
     Bliss
    0.07
    _UDP
    0.07
     بند
    0.07
     같이
    0.06
    αρα
    0.06
    ographs
    0.06
    一度
    0.06
     Toxic
    0.06
    fully
    0.06
    Activations Density 0.003%

    No Known Activations