© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 84636
    Prev
    Next
    INDEX
    Explanations

    @@

    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
    Rose
    -0.07
    мах
    -0.07
    她的
    -0.06
    脸
    -0.06
     samsung
    -0.06
    ,q
    -0.06
     kia
    -0.06
    278
    -0.06
    آخر
    -0.06
     элек
    -0.06
    POSITIVE LOGITS
    CTS
    0.08
    GetProcAddress
    0.08
     اهل
    0.07
    nostic
    0.07
    >`
    0.06
    _LT
    0.06
    gratis
    0.06
    .gwt
    0.06
     kür
    0.06
     CCT
    0.06
    Activations Density 0.001%

    No Known Activations