© 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. 27937
    Prev
    Next
    INDEX
    Explanations

    s

    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
     diesel
    -0.07
     commanding
    -0.06
     ')';↵
    -0.06
    922
    -0.06
     maiden
    -0.06
     Hooks
    -0.06
    :@""
    -0.06
    angen
    -0.06
     bulunur
    -0.06
    _update
    -0.06
    POSITIVE LOGITS
     Rue
    0.08
     اجرا
    0.06
     अप
    0.06
     rue
    0.06
    GV
    0.06
    ее
    0.06
    affen
    0.06
    时
    0.06
    �
    0.06
    igaret
    0.06
    Activations Density 0.009%

    No Known Activations