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. 35762
    Prev
    Next
    INDEX
    Explanations

    label

    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
    married
    -0.07
    affen
    -0.06
    SCREEN
    -0.06
    discussion
    -0.06
    ‌ش
    -0.06
    رده
    -0.06
    ズ
    -0.06
     Zap
    -0.06
     olan
    -0.06
    love
    -0.06
    POSITIVE LOGITS
     ;
    ↵
    ↵
    0.07
     reserved
    0.07
     pří
    0.07
    .querySelectorAll
    0.07
    (Yii
    0.07
    so
    0.06
    (words
    0.06
     locationManager
    0.06
     Fishing
    0.06
     bew
    0.06
    Activations Density 0.015%

    No Known Activations