© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 103796
    Prev
    Next
    INDEX
    Explanations

    percentages and statistics

    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
     lore
    -0.06
    uel
    -0.06
     chests
    -0.06
    した
    -0.06
    clud
    -0.06
     BACKGROUND
    -0.06
    purple
    -0.06
    鸡
    -0.06
     至
    -0.06
     سپس
    -0.06
    POSITIVE LOGITS
    HO
    0.07
    ho
    0.06
    -key
    0.06
    ()):
    0.06
    عل
    0.06
     Sweep
    0.06
     haul
    0.06
    _Info
    0.06
    ove
    0.06
     symmetric
    0.06
    Activations Density 0.274%

    No Known Activations