© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27-RESID-POST-AA
    11. 35785
    Prev
    Next
    INDEX
    Explanations

    Violent/negative events

    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
    Negative Logits
     buffers
    -0.07
    Với
    -0.06
     creek
    -0.06
     marg
    -0.06
     buffer
    -0.06
     Polar
    -0.06
     fastball
    -0.06
     Average
    -0.06
    ydı
    -0.06
    ()`
    -0.06
    POSITIVE LOGITS
     }}">
    0.07
     مدير
    0.06
     getattr
    0.06
    意义
    0.06
     ACM
    0.06
    ندر
    0.06
     Registers
    0.06
    108
    0.06
     wohl
    0.05
    )을
    0.05
    Activations Density 0.046%

    No Known Activations