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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 51285
    Prev
    Next
    INDEX
    Explanations

    Free Software Foundation

    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
    .Comm
    -0.06
     Из
    -0.06
     จาก
    -0.06
    _with
    -0.06
    	mouse
    -0.06
    ектора
    -0.06
    оре
    -0.06
     تنها
    -0.06
    γω
    -0.06
    _individual
    -0.06
    POSITIVE LOGITS
     opting
    0.07
     lange
    0.07
    CLICK
    0.07
     исключ
    0.07
    UILDER
    0.07
    契
    0.07
     号
    0.07
     prosperous
    0.07
     Isabel
    0.06
    <float
    0.06
    Activations Density 0.002%

    No Known Activations