© 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. 11-RESID-POST-AA
    11. 17637
    Prev
    Next
    INDEX
    Explanations

    people, especially women/children

    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_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
    licenses
    -0.07
    massage
    -0.07
     cùng
    -0.07
     т
    -0.06
     Tx
    -0.06
    .dataSource
    -0.06
     replied
    -0.06
    _POLL
    -0.06
     puesto
    -0.06
     ecosystem
    -0.06
    POSITIVE LOGITS
     належ
    0.06
    _compute
    0.06
    yük
    0.06
     deletes
    0.06
    (math
    0.06
    ентом
    0.06
    '>".$
    0.06
     reordered
    0.06
     JAXBElement
    0.05
     외
    0.05
    Activations Density 0.028%

    No Known Activations