© 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. 8728
    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
     exploits
    -0.08
    GT
    -0.07
     GPL
    -0.07
    ulant
    -0.07
    udded
    -0.06
    Enable
    -0.06
    London
    -0.06
            	↵
    -0.06
     hel
    -0.06
    éli
    -0.06
    POSITIVE LOGITS
    だって
    0.07
     xmlDoc
    0.07
    .EMAIL
    0.06
    (unique
    0.06
     Soap
    0.06
     Relationships
    0.06
     σας
    0.06
     说
    0.06
     asla
    0.06
     jailed
    0.06
    Activations Density 0.015%

    No Known Activations