© 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. 19-RESID-POST-AA
    11. 114968
    Prev
    Next
    INDEX
    Explanations

    caret

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    plings
    -0.07
    Endpoints
    -0.07
     bankrupt
    -0.06
    lng
    -0.06
    ío
    -0.06
    calls
    -0.06
    íveis
    -0.06
    Greetings
    -0.06
     önünde
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    !↵
    0.07
    )!↵
    0.07
     enforcement
    0.07
     %%↵
    0.07
     ).↵
    0.07
    iosity
    0.06
    feeding
    0.06
     معت
    0.06
     thế
    0.06
     USER
    0.06
    Activations Density 0.012%

    No Known Activations