© 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. 15-RESID-POST-AA
    11. 127539
    Prev
    Next
    INDEX
    Explanations

    escaping problems

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lik
    -0.07
    ドラ
    -0.06
    mui
    -0.06
     요
    -0.06
     Trem
    -0.06
    刷
    -0.06
     acciones
    -0.06
     сир
    -0.06
    μιο
    -0.06
    疾
    -0.06
    POSITIVE LOGITS
     beard
    0.06
    ute
    0.06
     posix
    0.06
    avou
    0.06
     analog
    0.06
    aceutical
    0.06
     debit
    0.06
     camera
    0.06
     adjustable
    0.06
     savedInstanceState
    0.06
    Activations Density 0.037%

    No Known Activations