© 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. 15-RESID-POST-AA
    11. 56618
    Prev
    Next
    INDEX
    Explanations

    Star

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    masters
    -0.06
     superficial
    -0.06
    ’an
    -0.06
    ari
    -0.06
    ิทธ
    -0.06
     elé
    -0.06
    uxtap
    -0.06
    Baseline
    -0.06
    ';';
    -0.06
    ToolTip
    -0.06
    POSITIVE LOGITS
     drive
    0.07
    文件
    0.07
     drives
    0.06
     Pretty
    0.06
    uez
    0.06
     MAKE
    0.06
     integrate
    0.06
     havoc
    0.06
    лением
    0.06
     Liber
    0.06
    Activations Density 0.002%

    No Known Activations