© 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. 70863
    Prev
    Next
    INDEX
    Explanations

    schedule

    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
    行政
    -0.06
    ียน
    -0.06
    /media
    -0.06
     sensory
    -0.06
     Пло
    -0.06
     skills
    -0.06
     squirrel
    -0.06
     Downs
    -0.06
     сна
    -0.06
    Tuple
    -0.06
    POSITIVE LOGITS
    marked
    0.06
     Erotic
    0.06
     Schedule
    0.06
    '},
    ↵
    0.06
     LSB
    0.06
    .Blocks
    0.06
    (double
    0.06
    .Home
    0.06
    /*----------------------------------------------------------------
    0.06
    変更
    0.06
    Activations Density 0.036%

    No Known Activations