© 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 EvalsExportsinterp-engineNEWAPI 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. 22898
    Prev
    Next
    INDEX
    Explanations

    main

    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
    estation
    -0.07
     inté
    -0.06
    _MODIFIED
    -0.06
    Risk
    -0.06
    _cube
    -0.06
     responsive
    -0.06
    ництва
    -0.06
    _and
    -0.06
     ET
    -0.06
    =Y
    -0.06
    POSITIVE LOGITS
     main
    0.14
     одерж
    0.07
     cửa
    0.07
    {(
    0.07
    _thresh
    0.07
     prime
    0.07
     outlined
    0.07
     principales
    0.07
    main
    0.07
     Main
    0.07
    Activations Density 0.022%

    No Known Activations