© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 121246
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Days
    -0.06
    งาน
    -0.06
    نتاج
    -0.06
     uname
    -0.06
     tours
    -0.06
    permissions
    -0.06
    texto
    -0.06
    وده
    -0.06
    	core
    -0.06
     Adapt
    -0.06
    POSITIVE LOGITS
     Orthodox
    0.07
     krat
    0.07
    ┬
    0.06
     contractors
    0.06
     registrar
    0.06
     Vig
    0.06
    нима
    0.06
     Troll
    0.06
    .comm
    0.06
    _collections
    0.06
    Activations Density 0.045%

    No Known Activations