© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 45486
    Prev
    Next
    INDEX
    Explanations

    365

    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
    ordinated
    -0.06
     Lower
    -0.06
     گفته
    -0.06
    chw
    -0.06
    /people
    -0.06
    awner
    -0.06
    often
    -0.06
     adultery
    -0.06
    West
    -0.06
     genocide
    -0.06
    POSITIVE LOGITS
    metro
    0.07
     stimulate
    0.06
     ROT
    0.06
     дум
    0.06
     thuốc
    0.06
     البر
    0.06
     条
    0.06
     금액
    0.06
     Mend
    0.06
     ك
    0.06
    Activations Density 0.012%

    No Known Activations