© 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. 30077
    Prev
    Next
    INDEX
    Explanations

    prevent

    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
     Tân
    -0.07
    сько
    -0.07
     citiz
    -0.07
     joy
    -0.07
     développ
    -0.06
    湿
    -0.06
     grandson
    -0.06
     Gordon
    -0.06
    oueur
    -0.06
    TRA
    -0.06
    POSITIVE LOGITS
    =default
    0.07
    .arrow
    0.07
     unrestricted
    0.07
    -script
    0.06
    _contents
    0.06
    rabilir
    0.06
    .Where
    0.06
     randomness
    0.06
    ']},↵
    0.06
     pys
    0.06
    Activations Density 0.015%

    No Known Activations