© 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. 3-RESID-POST-AA
    11. 93610
    Prev
    Next
    INDEX
    Explanations

    thin film transistors

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stressful
    -0.07
    las
    -0.06
     clipped
    -0.06
     rider
    -0.06
     сразу
    -0.06
     Malta
    -0.06
    unload
    -0.06
    цин
    -0.06
     vzdál
    -0.06
    iazza
    -0.06
    POSITIVE LOGITS
     PBS
    0.12
    PBS
    0.11
     Manson
    0.08
     chubby
    0.07
    CTYPE
    0.07
     documentary
    0.07
    249
    0.07
     LSD
    0.06
    234
    0.06
    LineColor
    0.06
    Activations Density 0.003%

    No Known Activations