Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104085
    Prev
    Next
    INDEX
    Explanations

    continental US

    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
    rames
    -0.07
     총
    -0.07
    /assets
    -0.07
    Employee
    -0.07
    titulo
    -0.07
    para
    -0.06
     spouse
    -0.06
    hazi
    -0.06
    EIF
    -0.06
     Depend
    -0.06
    POSITIVE LOGITS
     whites
    0.07
     gözlem
    0.06
     строк
    0.06
     стр
    0.06
    realloc
    0.06
    inks
    0.06
    INES
    0.06
     enhancements
    0.06
    	 	
    0.05
    punkt
    0.05
    Activations Density 0.006%

    No Known Activations