© 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. 115918
    Prev
    Next
    INDEX
    Explanations

    bullying or lying

    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
    haven
    -0.07
     pitchers
    -0.06
     Encore
    -0.06
     Tobias
    -0.06
    ущ
    -0.06
    icon
    -0.06
     quests
    -0.06
     zaz
    -0.06
    threat
    -0.06
     wager
    -0.06
    POSITIVE LOGITS
     bullying
    0.15
     bullied
    0.12
     bully
    0.09
     Bulld
    0.08
     eğit
    0.07
    typed
    0.06
     brutality
    0.06
     Bul
    0.06
     METH
    0.06
    DLL
    0.06
    Activations Density 0.003%

    No Known Activations