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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 72021
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency

    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
     Boeing
    -0.07
     accents
    -0.07
     BP
    -0.06
     Bain
    -0.06
    修改
    -0.06
     bor
    -0.06
     soak
    -0.06
    -box
    -0.06
     خدم
    -0.06
     calorie
    -0.06
    POSITIVE LOGITS
     Nhưng
    0.07
    Subscribe
    0.07
    τική
    0.06
    handle
    0.06
    donnees
    0.06
    аем
    0.06
    =Value
    0.06
     warns
    0.06
    τζ
    0.06
    ��
    0.06
    Activations Density 0.015%

    No Known Activations