© 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. 11-RESID-POST-AA
    6. 76587
    Prev
    Next
    INDEX
    Explanations

    world is difficult

    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
    signIn
    -0.07
     trimming
    -0.07
     Play
    -0.06
     critique
    -0.06
    	send
    -0.06
     qa
    -0.06
     Equality
    -0.06
     thanks
    -0.06
    hyper
    -0.06
    )"↵
    -0.06
    POSITIVE LOGITS
    uteč
    0.07
     tableLayoutPanel
    0.07
    ौ
    0.07
    DataExchange
    0.07
    .Exists
    0.06
    (col
    0.06
    _Details
    0.06
     UV
    0.06
     Ritual
    0.06
    childs
    0.06
    Activations Density 0.060%

    No Known Activations