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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 110157
    Prev
    Next
    INDEX
    Explanations

    [

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PR
    -0.07
     peptide
    -0.07
     Printer
    -0.06
    Under
    -0.06
     piece
    -0.06
    طار
    -0.06
     GOD
    -0.06
     mediums
    -0.06
     drought
    -0.06
     terminal
    -0.06
    POSITIVE LOGITS
    _home
    0.07
     IDirect
    0.06
    _production
    0.06
     UITableViewDelegate
    0.06
    ='#
    0.06
    /products
    0.06
     redistributed
    0.06
    :relative
    0.06
    _mc
    0.06
     keer
    0.06
    Activations Density 0.002%

    No Known Activations