© 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. 93674
    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
    rna
    -0.07
    ابد
    -0.07
     butt
    -0.07
    بد
    -0.06
    кадем
    -0.06
    .FormStartPosition
    -0.06
     apart
    -0.06
     allo
    -0.06
    Bern
    -0.06
     بالن
    -0.06
    POSITIVE LOGITS
    -clear
    0.07
    丰
    0.07
    _TOKEN
    0.06
     Associates
    0.06
     clearInterval
    0.06
     Yorkers
    0.06
    wright
    0.06
     associated
    0.06
     animals
    0.06
     견
    0.06
    Activations Density 0.015%

    No Known Activations