© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74832
    Prev
    Next
    INDEX
    Explanations

    том

    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
    .card
    -0.07
    ег
    -0.06
    (levels
    -0.06
    Pay
    -0.06
     Bring
    -0.06
    connect
    -0.06
    ,{
    -0.06
    asket
    -0.06
     شهرستان
    -0.06
     Arg
    -0.06
    POSITIVE LOGITS
    ."},↵
    0.08
    ‌دهد
    0.08
     работает
    0.08
     donn
    0.07
     того
    0.07
    ITLE
    0.07
    曰
    0.07
     WELL
    0.07
     이루
    0.07
     том
    0.07
    Activations Density 0.027%

    No Known Activations