© 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. 46826
    Prev
    Next
    INDEX
    Explanations

    filenames and naming conventions

    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
     weighting
    -0.07
    indh
    -0.07
    shirt
    -0.07
     modulus
    -0.07
     less
    -0.07
     catalog
    -0.06
     statue
    -0.06
    _ack
    -0.06
    ystery
    -0.06
     module
    -0.06
    POSITIVE LOGITS
     kaldı
    0.06
     zona
    0.06
     ήταν
    0.06
     Κό
    0.06
     fatal
    0.06
     cria
    0.06
    entario
    0.06
     recibir
    0.06
    asted
    0.06
     Μετα
    0.06
    Activations Density 0.068%

    No Known Activations