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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 9980
    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_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
    argc
    -0.07
     todos
    -0.07
     app
    -0.07
    .Database
    -0.07
     louis
    -0.07
     deux
    -0.07
    十三
    -0.07
    GET
    -0.07
     económ
    -0.07
     microsoft
    -0.06
    POSITIVE LOGITS
    iability
    0.06
    Goods
    0.06
    [Any
    0.06
     Gifts
    0.06
     szy
    0.06
    ,由
    0.06
    ffects
    0.06
     payable
    0.05
    Minor
    0.05
    ิพ
    0.05
    Activations Density 0.003%

    No Known Activations