© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25476
    Prev
    Next
    INDEX
    Explanations

    Brazil

    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
    .scalatest
    -0.07
    撃
    -0.06
    crear
    -0.06
    respons
    -0.06
    Minute
    -0.06
    ِي
    -0.06
    ighet
    -0.06
    _Resource
    -0.06
    슨
    -0.06
     telefon
    -0.06
    POSITIVE LOGITS
    Brazil
    0.10
     Brazil
    0.10
     Brazilian
    0.08
     Brasil
    0.08
     BH
    0.07
     brasile
    0.07
    THEN
    0.07
     THEN
    0.07
     inland
    0.06
    OOSE
    0.06
    Activations Density 0.036%

    No Known Activations