© 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. 23-RESID-POST-AA
    11. 62808
    Prev
    Next
    INDEX
    Explanations

    published

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     yard
    -0.07
     mixed
    -0.07
     picker
    -0.07
     texture
    -0.07
     gallery
    -0.06
    hub
    -0.06
     salad
    -0.06
    通信
    -0.06
     ferment
    -0.06
     lined
    -0.06
    POSITIVE LOGITS
     ´
    0.07
     disappearing
    0.07
    .TODO
    0.07
    Whitespace
    0.06
    _ASSUME
    0.06
    kept
    0.06
     çıkar
    0.06
     إليه
    0.06
    ヾ
    0.06
    озвращает
    0.06
    Activations Density 0.002%

    No Known Activations