Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 57506
    Prev
    Next
    INDEX
    Explanations

    fitness trackers

    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
     leasing
    -0.07
    -ph
    -0.06
    rophy
    -0.06
    itin
    -0.06
    ần
    -0.06
    Objects
    -0.06
     typing
    -0.06
    Germany
    -0.06
     livro
    -0.06
    POSITIVE LOGITS
     أيض
    0.06
    OCUMENT
    0.06
     frontend
    0.06
     perm
    0.06
     реб
    0.06
    &)↵
    0.06
     zach
    0.06
    OMBRE
    0.06
     queryInterface
    0.06
    计算
    0.06
    Activations Density 0.042%

    No Known Activations