© 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. 11-RESID-POST-AA
    11. 101159
    Prev
    Next
    INDEX
    Explanations

    houses

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Πο
    -0.07
    371
    -0.07
    .mark
    -0.07
     aden
    -0.06
    vro
    -0.06
     Esther
    -0.06
    (status
    -0.06
     manga
    -0.06
     ceramic
    -0.06
    printStats
    -0.06
    POSITIVE LOGITS
    wise
    0.06
    ward
    0.06
     recurse
    0.06
    /rec
    0.06
    backs
    0.06
     Resident
    0.06
    uded
    0.06
     unlaw
    0.06
    -shell
    0.06
     Appeal
    0.06
    Activations Density 0.004%

    No Known Activations