© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9716
    Prev
    Next
    INDEX
    Explanations

    memorization and -ize, -izing

    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
     examinations
    -0.07
     кафед
    -0.07
     Ο
    -0.07
     Directorate
    -0.07
     쓰
    -0.06
     Speaking
    -0.06
    	IL
    -0.06
     chaud
    -0.06
     last
    -0.06
     rés
    -0.06
    POSITIVE LOGITS
     Gee
    0.06
    _iface
    0.06
    ательно
    0.06
     wszyst
    0.06
    gency
    0.06
    EZ
    0.06
     optimizations
    0.06
    ション
    0.06
    stå
    0.06
    ussions
    0.06
    Activations Density 0.022%

    No Known Activations