© 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. 3-RESID-POST-AA
    11. 95648
    Prev
    Next
    INDEX
    Explanations

    weighs

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saint
    -0.06
    NOW
    -0.06
    创新
    -0.06
    urity
    -0.06
     lorsque
    -0.06
     supernatural
    -0.06
     nast
    -0.06
    เลข
    -0.06
     ist
    -0.06
    hot
    -0.06
    POSITIVE LOGITS
     weighs
    0.22
     weigh
    0.21
    weigh
    0.08
     weighed
    0.07
    .File
    0.07
     quadratic
    0.07
     Specifications
    0.07
    .Equals
    0.06
    DOMAIN
    0.06
     bağlantılar
    0.06
    Activations Density 0.002%

    No Known Activations