© 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. 7-RESID-POST-AA
    6. 32744
    Prev
    Next
    INDEX
    Explanations

    code

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     К
    -0.07
    بینی
    -0.07
    卻
    -0.07
     deepen
    -0.07
     cihaz
    -0.07
     lange
    -0.07
     by
    -0.07
     vyz
    -0.07
    .pos
    -0.06
     Principle
    -0.06
    POSITIVE LOGITS
    impse
    0.06
    رج
    0.06
     shields
    0.06
    MUX
    0.06
    ��
    0.06
    _GOOD
    0.05
    囲
    0.05
     TED
    0.05
     briefly
    0.05
    ield
    0.05
    Activations Density 0.017%

    No Known Activations