© 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. 15-RESID-POST-AA
    11. 37554
    Prev
    Next
    INDEX
    Explanations

    Code/Configurations

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DET
    -0.07
    stdint
    -0.07
    .ColumnHeader
    -0.07
    ffset
    -0.06
    diğini
    -0.06
     tqdm
    -0.06
     Black
    -0.06
    bps
    -0.06
    _callback
    -0.06
     identified
    -0.06
    POSITIVE LOGITS
    оже
    0.06
    =M
    0.06
    heure
    0.06
     берем
    0.06
     royalty
    0.06
     Kaynak
    0.06
    ね
    0.06
    ELY
    0.06
    Corn
    0.06
     النو
    0.06
    Activations Density 0.124%

    No Known Activations