© 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. 15-RESID-POST-AA
    11. 109210
    Prev
    Next
    INDEX
    Explanations

    Author names

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    takes
    -0.07
     lain
    -0.07
     Robots
    -0.07
    	public
    -0.06
    ubes
    -0.06
    013
    -0.06
     Phelps
    -0.06
    	F
    -0.06
     theatrical
    -0.06
    wner
    -0.06
    POSITIVE LOGITS
     OpenSSL
    0.06
     koruy
    0.06
     Fach
    0.06
    ?-
    0.06
    ablytyped
    0.06
    Declare
    0.06
     upgrading
    0.06
     ارتفاع
    0.06
    重複重複
    0.06
    抽
    0.06
    Activations Density 0.041%

    No Known Activations