© 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. 15-RESID-POST-AA
    6. 16093
    Prev
    Next
    INDEX
    Explanations

    Shame

    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
     PNG
    -0.07
     μια
    -0.07
     ful
    -0.07
     analyzing
    -0.06
    是一
    -0.06
    ρούν
    -0.06
    cri
    -0.06
    Export
    -0.06
     něj
    -0.06
    ために
    -0.06
    POSITIVE LOGITS
    _BASIC
    0.07
     newRow
    0.07
    ミュ
    0.06
     gastro
    0.06
     "]");↵
    0.06
    feeding
    0.06
    _
    ↵
    0.06
     mating
    0.06
     medically
    0.06
    อกจากน
    0.06
    Activations Density 0.000%

    No Known Activations