© 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. 93807
    Prev
    Next
    INDEX
    Explanations

    protective

    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
     sap
    -0.07
     TT
    -0.07
    แท
    -0.07
    lerle
    -0.06
    illes
    -0.06
     dari
    -0.06
     intim
    -0.06
     haci
    -0.06
     comple
    -0.06
    _SETTING
    -0.06
    POSITIVE LOGITS
     protective
    0.08
     Newman
    0.07
    	protected
    0.06
     Obesity
    0.06
     Lowe
    0.06
     rebounds
    0.06
    -East
    0.06
    -fiction
    0.06
     Stmt
    0.06
    imization
    0.06
    Activations Density 0.001%

    No Known Activations