© 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. 101723
    Prev
    Next
    INDEX
    Explanations

    with

    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
    LANGADM
    -0.07
    .Th
    -0.07
     confort
    -0.06
    深
    -0.06
    .onActivityResult
    -0.06
     stares
    -0.06
     tart
    -0.06
    Nullable
    -0.06
     baptized
    -0.06
    _nl
    -0.06
    POSITIVE LOGITS
     Executive
    0.06
    -picture
    0.06
    -push
    0.06
     Fox
    0.06
    .Adapter
    0.06
     Lee
    0.06
    izzle
    0.06
     Dude
    0.06
    _result
    0.06
     Reflect
    0.06
    Activations Density 0.008%

    No Known Activations