Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 4980
    Prev
    Next
    INDEX
    Explanations

    and/while

    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
    {{{
    -0.07
    CTest
    -0.07
     SVG
    -0.07
    ..↵↵↵↵
    -0.07
    えた
    -0.06
     coron
    -0.06
    ....↵↵
    -0.06
     VID
    -0.06
    _classes
    -0.06
    fried
    -0.06
    POSITIVE LOGITS
     Compass
    0.06
    085
    0.06
     celebrities
    0.06
    ilk
    0.06
     Birleşik
    0.06
    clear
    0.06
     yaklaşık
    0.06
     الاقتص
    0.06
     اقتصادی
    0.06
    	initialize
    0.06
    Activations Density 0.002%

    No Known Activations