© 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. 93722
    Prev
    Next
    INDEX
    Explanations

    ody

    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
     Bout
    -0.06
     Consumption
    -0.06
     Garage
    -0.06
    Iteration
    -0.06
    Constants
    -0.06
    .TRA
    -0.06
    561
    -0.06
    érica
    -0.06
     افر
    -0.06
    Provide
    -0.06
    POSITIVE LOGITS
     Moody
    0.16
    ody
    0.14
    ODY
    0.10
    ddy
    0.07
     financing
    0.07
    .loading
    0.06
     effet
    0.06
    /lgpl
    0.06
     Finance
    0.06
     Wal
    0.06
    Activations Density 0.001%

    No Known Activations