© 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. 23-RESID-POST-AA
    11. 67363
    Prev
    Next
    INDEX
    Explanations

    code, data, debugging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     swapped
    -0.07
    Github
    -0.07
     Tw
    -0.07
    шел
    -0.06
    >(*
    -0.06
     cuanto
    -0.06
    _side
    -0.06
    -shirt
    -0.06
     mdi
    -0.06
    riday
    -0.06
    POSITIVE LOGITS
    ах
    0.06
    قات
    0.06
     fertile
    0.06
    шин
    0.06
    .database
    0.06
    \Foundation
    0.06
     मल
    0.06
    达
    0.06
    ance
    0.06
     letra
    0.06
    Activations Density 0.038%

    No Known Activations