© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 72279
    Prev
    Next
    INDEX
    Explanations

    DEVELO

    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
     Lý
    -0.06
    elsing
    -0.06
    afia
    -0.06
    لیت
    -0.06
    Fs
    -0.06
    Capabilities
    -0.06
     verd
    -0.06
    ildo
    -0.06
    ursive
    -0.06
     institutes
    -0.06
    POSITIVE LOGITS
    .Magic
    0.06
     IMAGES
    0.06
     MATLAB
    0.06
     każ
    0.06
     UNUSED
    0.06
     TRUE
    0.06
     ALIGN
    0.06
    .rep
    0.06
    .mod
    0.06
    ```
    0.06
    Activations Density 1.100%

    No Known Activations