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. 11-RESID-POST-AA
    6. 21835
    Prev
    Next
    INDEX
    Explanations

    it

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    زية
    -0.07
     اصفه
    -0.06
     MySqlCommand
    -0.06
     yếu
    -0.06
     casa
    -0.06
    Poor
    -0.06
    .multi
    -0.06
    ID
    -0.06
    ariat
    -0.06
    ycling
    -0.06
    POSITIVE LOGITS
     adventurers
    0.07
     attributed
    0.06
     advisors
    0.06
     precisely
    0.06
     thumbnails
    0.06
     Align
    0.06
    ่ง
    0.06
    imately
    0.06
    ınızda
    0.06
     COMM
    0.06
    Activations Density 0.091%

    No Known Activations