© 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. 7-RESID-POST-AA
    11. 80154
    Prev
    Next
    INDEX
    Explanations

    health, activity, and destinations

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /mod
    -0.07
     inward
    -0.07
    	row
    -0.07
     point
    -0.06
    ango
    -0.06
     AppBundle
    -0.06
    一般
    -0.06
     fact
    -0.06
    enario
    -0.06
     Bobby
    -0.06
    POSITIVE LOGITS
     majors
    0.06
     Formal
    0.06
     와
    0.06
     );↵↵
    0.05
     Τα
    0.05
     separators
    0.05
    Sorted
    0.05
     Beetle
    0.05
    'ın
    0.05
    enschaft
    0.05
    Activations Density 0.141%

    No Known Activations