© 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. 93760
    Prev
    Next
    INDEX
    Explanations

    scissors

    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
     banda
    -0.07
    QA
    -0.06
    64
    -0.06
    -В
    -0.06
     Peanut
    -0.06
    bu
    -0.06
    ADF
    -0.06
     Weekly
    -0.06
    **
    -0.06
    .Refresh
    -0.06
    POSITIVE LOGITS
     scissors
    0.16
    issors
    0.13
    issor
    0.10
     pencils
    0.07
    исс
    0.07
     دور
    0.07
     mater
    0.06
     operations
    0.06
     рес
    0.06
     Bij
    0.06
    Activations Density 0.001%

    No Known Activations