© 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. 19-RESID-POST-AA
    11. 113638
    Prev
    Next
    INDEX
    Explanations

    Obs

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пло
    -0.06
     сайте
    -0.06
     Yo
    -0.06
     celebrate
    -0.06
     toString
    -0.06
     técn
    -0.06
     Put
    -0.06
    ocolate
    -0.06
     nunca
    -0.06
     inadequate
    -0.06
    POSITIVE LOGITS
    ATTERN
    0.07
    .MiddleCenter
    0.07
    zing
    0.06
    відом
    0.06
     Шев
    0.06
     sırada
    0.06
     distraction
    0.06
     обесп
    0.06
    ीख
    0.06
    ź
    0.06
    Activations Density 0.008%

    No Known Activations