© 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. 59551
    Prev
    Next
    INDEX
    Explanations

    write

    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
    Pad
    -0.08
     abc
    -0.07
    Campo
    -0.07
     mars
    -0.06
     oo
    -0.06
     Mercy
    -0.06
     armour
    -0.06
     Temple
    -0.06
    uma
    -0.06
     cush
    -0.06
    POSITIVE LOGITS
     write
    0.17
     writing
    0.15
     written
    0.13
     Write
    0.13
     writer
    0.12
     Writing
    0.12
    write
    0.12
     writers
    0.12
    Writer
    0.12
    Write
    0.11
    Activations Density 0.099%

    No Known Activations