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. 36217
    Prev
    Next
    INDEX
    Explanations

    .Request

    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
     appar
    -0.07
    Whether
    -0.06
    Son
    -0.06
    .fragment
    -0.06
    endale
    -0.06
    _study
    -0.06
    .ProgressBar
    -0.06
     Belgian
    -0.06
    эт
    -0.06
    -course
    -0.06
    POSITIVE LOGITS
     диаг
    0.07
     Retro
    0.07
    صل
    0.07
    شاء
    0.07
     Painter
    0.07
     지금
    0.06
    ческого
    0.06
     cải
    0.06
    Apellido
    0.06
     Master
    0.06
    Activations Density 0.003%

    No Known Activations