© 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. 11-RESID-POST-AA
    11. 93923
    Prev
    Next
    INDEX
    Explanations

    to

    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
    施工
    -0.07
     SolidColorBrush
    -0.07
     sprint
    -0.06
    ProductId
    -0.06
     stere
    -0.06
     نیز
    -0.06
    _flash
    -0.06
    获
    -0.06
    olen
    -0.06
    rible
    -0.06
    POSITIVE LOGITS
    ('/')[
    0.07
    estination
    0.06
    ’T
    0.06
     může
    0.06
     анг
    0.06
    _MEMBER
    0.06
    	account
    0.06
    .n
    0.06
     RESOURCE
    0.06
    }'.
    0.06
    Activations Density 0.019%

    No Known Activations