© 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. 93970
    Prev
    Next
    INDEX
    Explanations

    Foreign language replies

    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
     anal
    -0.06
     bundle
    -0.06
    	
↵
↵
    -0.06
    -cal
    -0.06
    izzo
    -0.06
     pur
    -0.06
     Anders
    -0.06
    属性
    -0.06
     Suff
    -0.06
     Saturdays
    -0.06
    POSITIVE LOGITS
     resposta
    0.08
     response
    0.07
    ění
    0.07
     ответ
    0.07
     reply
    0.07
     answer
    0.07
    >',↵
    0.07
    ewater
    0.07
    _PATTERN
    0.07
    %',
    0.07
    Activations Density 0.049%

    No Known Activations