© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 77313
    Prev
    Next
    INDEX
    Explanations

    education

    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
    AIN
    -0.06
     xảy
    -0.06
    -М
    -0.06
    ))
↵
    -0.06
    絶
    -0.06
    _queue
    -0.05
    ToEnd
    -0.05
    QUE
    -0.05
     erkek
    -0.05
    喊
    -0.05
    POSITIVE LOGITS
    vertical
    0.07
    apper
    0.07
     teacher
    0.07
     kaynağı
    0.07
    盒
    0.06
    .spacing
    0.06
     Grad
    0.06
    σταση
    0.06
     Mild
    0.06
    .firstName
    0.06
    Activations Density 0.023%

    No Known Activations