© 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. 35639
    Prev
    Next
    INDEX
    Explanations

    punishment

    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
     myths
    -0.07
     foam
    -0.07
     roadway
    -0.07
     Dee
    -0.06
    ются
    -0.06
     varying
    -0.06
    12
    -0.06
     highly
    -0.06
     Realty
    -0.06
     observations
    -0.06
    POSITIVE LOGITS
     punish
    0.09
     punished
    0.07
     лиш
    0.07
     Pdf
    0.07
    _GAME
    0.07
    lesh
    0.07
     punishments
    0.07
     Ank
    0.07
    пис
    0.07
     arrests
    0.07
    Activations Density 0.005%

    No Known Activations