© 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. 19-RESID-POST-AA
    11. 32977
    Prev
    Next
    INDEX
    Explanations

    8

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     birlikte
    -0.07
    dehy
    -0.06
     cabins
    -0.06
    اطل
    -0.06
    sanız
    -0.06
     أبريل
    -0.06
     NUMBER
    -0.06
     PLAYER
    -0.06
    Я
    -0.06
     бра
    -0.06
    POSITIVE LOGITS
     acquisitions
    0.07
    _weapon
    0.07
     dataSource
    0.06
    modele
    0.06
     getting
    0.06
     dollars
    0.06
    阪
    0.06
    浩
    0.06
    Raster
    0.06
    ignite
    0.06
    Activations Density 0.001%

    No Known Activations