© 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. 72445
    Prev
    Next
    INDEX
    Explanations

    control

    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
     Flour
    -0.07
    될
    -0.07
     Heard
    -0.06
     lành
    -0.06
     perception
    -0.06
     isot
    -0.06
     siege
    -0.06
    gre
    -0.06
    (test
    -0.06
     Merc
    -0.06
    POSITIVE LOGITS
     PCIe
    0.07
     getState
    0.06
    :indexPath
    0.06
    чества
    0.06
    stitial
    0.06
     Neptune
    0.06
     حسین
    0.06
    τητα
    0.06
     Holland
    0.06
    スター
    0.06
    Activations Density 0.015%

    No Known Activations