© 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. 7-RESID-POST-AA
    11. 79817
    Prev
    Next
    INDEX
    Explanations

    pathetic

    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
    Negative Logits
    _index
    -0.07
    ้อม
    -0.06
    _CRITICAL
    -0.06
     chlor
    -0.06
    ernal
    -0.06
    macro
    -0.06
     Daha
    -0.06
     Stra
    -0.06
    Alan
    -0.06
    (digits
    -0.06
    POSITIVE LOGITS
     pathetic
    0.12
     miserable
    0.08
     wrappers
    0.07
     OWN
    0.07
     trag
    0.07
    .q
    0.06
     WX
    0.06
     proportion
    0.06
     obsess
    0.06
     Mirror
    0.06
    Activations Density 0.008%

    No Known Activations