© 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. 51364
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     ошиб
    -0.07
    addError
    -0.07
    环境
    -0.07
     Pearce
    -0.07
    دارة
    -0.06
    tracts
    -0.06
    .det
    -0.06
     Illegal
    -0.06
    Strike
    -0.06
     Nodes
    -0.06
    POSITIVE LOGITS
    、一
    0.07
     oyun
    0.06
    ayım
    0.06
     دوب
    0.06
    /sw
    0.06
     attributed
    0.06
     nuevas
    0.06
    би
    0.06
    -strip
    0.06
    電
    0.06
    Activations Density 0.022%

    No Known Activations