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. 15-RESID-POST-AA
    6. 110945
    Prev
    Next
    INDEX
    Explanations

    Jewelry and accessories

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _arc
    -0.07
    _m
    -0.07
    RoleId
    -0.06
    _D
    -0.06
    sin
    -0.06
     Sm
    -0.06
    Seq
    -0.06
    ScrollIndicator
    -0.06
     Kush
    -0.06
    aphore
    -0.06
    POSITIVE LOGITS
     bị
    0.07
    جن
    0.06
     Fragment
    0.06
     artifacts
    0.06
    ọn
    0.06
     Mahar
    0.06
    شم
    0.06
     naval
    0.06
     taşım
    0.06
     роботи
    0.06
    Activations Density 0.041%

    No Known Activations