© 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. 7-RESID-POST-AA
    11. 93927
    Prev
    Next
    INDEX
    Explanations

    object

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     で
    -0.06
    /sample
    -0.06
    uální
    -0.06
    passes
    -0.06
     국내
    -0.06
    /to
    -0.06
     wcs
    -0.06
    aved
    -0.06
     queens
    -0.06
    chan
    -0.06
    POSITIVE LOGITS
    ]interface
    0.10
     Museum
    0.07
    ucursal
    0.07
     इ
    0.07
     adım
    0.07
    mob
    0.06
    useum
    0.06
     забезпеч
    0.06
    -instance
    0.06
     AnyObject
    0.06
    Activations Density 0.001%

    No Known Activations