© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 8712
    Prev
    Next
    INDEX
    Explanations

    examination

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atör
    -0.07
    ensex
    -0.07
     Give
    -0.07
     placed
    -0.07
    ¯¯¯¯
    -0.06
     رسمی
    -0.06
    lech
    -0.06
     wicked
    -0.06
     büyük
    -0.06
     Reserve
    -0.06
    POSITIVE LOGITS
    /ayushman
    0.07
    minster
    0.07
    floating
    0.07
    ’yi
    0.06
    omid
    0.06
     GAP
    0.06
     фрукт
    0.06
     が
    0.06
    ”的
    0.06
    اسية
    0.06
    Activations Density 0.026%

    No Known Activations