© 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. 94093
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ंदर
    -0.06
    ンデ
    -0.06
    ंध
    -0.06
    amel
    -0.06
     polish
    -0.06
     від
    -0.06
     human
    -0.06
     wipes
    -0.06
    콜
    -0.06
     Auto
    -0.06
    POSITIVE LOGITS
     apologies
    0.06
     XCTAssert
    0.06
    　↵
    0.06
     decent
    0.06
     Myth
    0.06
    ('../../../
    0.06
    .series
    0.06
     चर
    0.06
     dildo
    0.06
    絶
    0.06
    Activations Density 0.078%

    No Known Activations