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. 80985
    Prev
    Next
    INDEX
    Explanations

    vascular

    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
     Little
    -0.07
    аблиц
    -0.07
    _rows
    -0.07
    QRST
    -0.07
    rote
    -0.07
    ood
    -0.07
     ______
    -0.07
     superst
    -0.07
     senin
    -0.06
    alloween
    -0.06
    POSITIVE LOGITS
     vascular
    0.09
     muc
    0.07
    /UIKit
    0.06
     eventually
    0.06
     oxygen
    0.06
    .fhir
    0.06
    Configurer
    0.06
     vüc
    0.06
    يا
    0.06
     DataSet
    0.06
    Activations Density 0.003%

    No Known Activations