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. 81095
    Prev
    Next
    INDEX
    Explanations

    m

    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
     Libyan
    -0.07
    ubar
    -0.06
    影
    -0.06
    ungan
    -0.06
         
    -0.06
     Jetzt
    -0.06
    Mos
    -0.06
    реп
    -0.06
    icional
    -0.06
    ์)
    -0.06
    POSITIVE LOGITS
    』↵↵
    0.07
     우리
    0.06
    \Catalog
    0.06
    ↵    ↵↵
    0.06
    (serializer
    0.06
    terraform
    0.06
    [v
    0.06
    childNodes
    0.06
     ComboBox
    0.06
    .BackColor
    0.06
    Activations Density 0.025%

    No Known Activations