© 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 EvalsExportsinterp-engineNEWAPI 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. 101761
    Prev
    Next
    INDEX
    Explanations

    brittle

    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
     UA
    -0.07
    Narr
    -0.06
     sexuales
    -0.06
     دع
    -0.06
     marching
    -0.06
    -ups
    -0.06
     Ferry
    -0.06
     sacr
    -0.06
    _gamma
    -0.06
    -ion
    -0.06
    POSITIVE LOGITS
     brittle
    0.07
     ledna
    0.07
     dette
    0.07
     EventType
    0.06
     mismo
    0.06
     deserialize
    0.06
    isseur
    0.06
     tangible
    0.06
    <Message
    0.06
    author
    0.06
    Activations Density 0.003%

    No Known Activations