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. 118353
    Prev
    Next
    INDEX
    Explanations

    enveloped

    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
     Tara
    -0.07
    short
    -0.07
    ecess
    -0.07
    uição
    -0.07
    .YES
    -0.06
    有限公司
    -0.06
     علی
    -0.06
    CellStyle
    -0.06
    aría
    -0.06
     DV
    -0.06
    POSITIVE LOGITS
     playoff
    0.07
     Formatting
    0.07
    /x
    0.06
    _Ex
    0.06
    (scroll
    0.06
    .broadcast
    0.06
     ops
    0.06
     tattoos
    0.06
     moy
    0.06
     to
    0.06
    Activations Density 0.001%

    No Known Activations