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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 54527
    Prev
    Next
    INDEX
    Explanations

    code

    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
     �
    -0.07
    必要
    -0.07
    /job
    -0.06
    producer
    -0.06
    spy
    -0.06
     raping
    -0.06
     Peel
    -0.06
    ionage
    -0.06
    sequelize
    -0.06
    しく
    -0.06
    POSITIVE LOGITS
    ़े
    0.08
    rodní
    0.08
     casa
    0.07
    .register
    0.07
    _hex
    0.06
    очные
    0.06
     tyto
    0.06
     yüzyıl
    0.06
     cate
    0.06
    ٍ
    0.06
    Activations Density 0.068%

    No Known Activations