© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126071
    Prev
    Next
    INDEX
    Explanations

    grep

    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
     Cube
    -0.07
    ayload
    -0.07
     silky
    -0.06
    ifix
    -0.06
    ]={↵
    -0.06
     basin
    -0.06
    CON
    -0.06
    final
    -0.06
     cheated
    -0.06
     workbook
    -0.06
    POSITIVE LOGITS
    grep
    0.13
     grep
    0.12
    XHR
    0.07
    (hwnd
    0.07
     getView
    0.06
     errno
    0.06
    href
    0.06
     겁
    0.06
     derivatives
    0.06
     sparkling
    0.06
    Activations Density 0.002%

    No Known Activations