© 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. 11-RESID-POST-AA
    11. 80069
    Prev
    Next
    INDEX
    Explanations

    medical studies

    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
    불
    -0.06
    	vm
    -0.06
    usters
    -0.06
    雨
    -0.06
    коп
    -0.06
    (',')[
    -0.06
     isSelected
    -0.06
    .square
    -0.06
     اون
    -0.06
     언제
    -0.06
    POSITIVE LOGITS
    .BatchNorm
    0.07
     intric
    0.07
     guit
    0.06
     DIN
    0.06
     engages
    0.06
     Honolulu
    0.06
    _code
    0.06
     surprise
    0.06
     twink
    0.06
    ตาม
    0.06
    Activations Density 0.101%

    No Known Activations