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. 7-RESID-POST-AA
    6. 129590
    Prev
    Next
    INDEX
    Explanations

    create

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ownership
    -0.07
    ξει
    -0.06
    われた
    -0.06
     McKay
    -0.06
     }}">{{
    -0.06
     지방
    -0.06
    ними
    -0.06
    arshal
    -0.06
     Moines
    -0.06
    핀
    -0.06
    POSITIVE LOGITS
    .pb
    0.07
     acknowledge
    0.07
     pleaded
    0.07
    高校
    0.06
    ียงใหม
    0.06
    _add
    0.06
     çarp
    0.06
     atheist
    0.06
     інформа
    0.06
     medic
    0.06
    Activations Density 0.013%

    No Known Activations