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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 35349
    Prev
    Next
    INDEX
    Explanations

    with

    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
     Assoc
    -0.07
     shiny
    -0.06
     acı
    -0.06
    -pages
    -0.06
    159
    -0.06
    Disposable
    -0.06
    Hold
    -0.06
    mayın
    -0.06
     więcej
    -0.06
    -folder
    -0.06
    POSITIVE LOGITS
    (e
    0.07
    úc
    0.06
     Always
    0.06
     Function
    0.06
    ightly
    0.06
    rahim
    0.06
    盘
    0.06
    ъем
    0.06
     술
    0.06
    -directed
    0.06
    Activations Density 0.001%

    No Known Activations