© 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. 11-RESID-POST-AA
    6. 89543
    Prev
    Next
    INDEX
    Explanations

    Envy/Jealousy

    np_max-act · gemini-2.0-flash

    The neuron lights up on explicit sexual or erotic content.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rosen
    -0.07
    (Room
    -0.06
     liqu
    -0.06
    アップ
    -0.06
    >R
    -0.06
    -found
    -0.06
     조선
    -0.06
     ECC
    -0.06
    (Common
    -0.06
    (Product
    -0.06
    POSITIVE LOGITS
     envy
    0.10
     jealous
    0.10
     jealousy
    0.09
     ई
    0.07
     coveted
    0.07
     původ
    0.07
     hatta
    0.07
    ovah
    0.07
    Neil
    0.07
    یتی
    0.07
    Activations Density 0.005%

    No Known Activations