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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 80826
    Prev
    Next
    INDEX
    Explanations

    astronomy

    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
    .KeyCode
    -0.07
    .createdAt
    -0.06
    伍
    -0.06
     kutje
    -0.06
     kos
    -0.06
     Accessed
    -0.06
    作品
    -0.06
     бра
    -0.06
    endereco
    -0.06
     enviado
    -0.06
    POSITIVE LOGITS
     nomine
    0.07
    US
    0.06
    SSERT
    0.06
    σι
    0.06
    ชาย
    0.06
    eted
    0.06
    odial
    0.06
    \Component
    0.06
    ड़
    0.06
    huge
    0.06
    Activations Density 0.015%

    No Known Activations