© 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. 112910
    Prev
    Next
    INDEX
    Explanations

    ViewBag

    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
    洞
    -0.07
     tasted
    -0.06
     نظامی
    -0.06
    灭
    -0.06
     Autumn
    -0.06
    tolower
    -0.06
     stret
    -0.06
    ières
    -0.06
    embr
    -0.06
    ://"
    -0.06
    POSITIVE LOGITS
     ViewBag
    0.15
     Bag
    0.07
    Bag
    0.07
    VP
    0.07
     ViewData
    0.07
     bag
    0.07
    -за
    0.06
    Voice
    0.06
    b
    0.06
    big
    0.06
    Activations Density 0.001%

    No Known Activations