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. 104125
    Prev
    Next
    INDEX
    Explanations

    popularity

    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
    Williams
    -0.07
     qu
    -0.07
     encounter
    -0.07
    upy
    -0.07
     Fak
    -0.07
     tlak
    -0.07
    カー
    -0.06
     gays
    -0.06
     Поль
    -0.06
     merger
    -0.06
    POSITIVE LOGITS
    (Model
    0.07
     Ε
    0.07
     عکس
    0.07
     значение
    0.06
    .Exists
    0.06
    ствует
    0.06
    .execSQL
    0.06
     gridView
    0.06
    ersonic
    0.06
     awaited
    0.06
    Activations Density 0.041%

    No Known Activations