© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 84390
    Prev
    Next
    INDEX
    Explanations

    quality

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    と思
    -0.06
    	for
    -0.06
    project
    -0.06
    =$(
    -0.06
    -python
    -0.06
    -us
    -0.06
     Theo
    -0.06
     Yani
    -0.06
     opi
    -0.06
    	while
    -0.06
    POSITIVE LOGITS
     Glock
    0.06
    圭圭
    0.06
     München
    0.06
     Twins
    0.06
    公共
    0.06
     Wooden
    0.06
     �
    0.06
     Patent
    0.06
    iện
    0.06
     модели
    0.06
    Activations Density 0.018%

    No Known Activations