© 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. 92753
    Prev
    Next
    INDEX
    Explanations

    achieved

    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
    软
    -0.07
     infinite
    -0.07
    lando
    -0.07
     것으로
    -0.06
    .sep
    -0.06
    _first
    -0.06
    証
    -0.06
    е�
    -0.06
     role
    -0.06
     precondition
    -0.06
    POSITIVE LOGITS
    WebResponse
    0.06
    _inventory
    0.06
    ینه
    0.06
    Tools
    0.06
     VT
    0.06
     bundled
    0.06
    announcement
    0.06
    ADATA
    0.06
     konu
    0.06
    ент
    0.06
    Activations Density 0.014%

    No Known Activations