© 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. 15-RESID-POST-AA
    11. 45388
    Prev
    Next
    INDEX
    Explanations

    file data

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     takže
    -0.07
     mně
    -0.07
    cı
    -0.07
    舌
    -0.07
    شت
    -0.06
    _dept
    -0.06
    ávě
    -0.06
     言
    -0.06
     başv
    -0.06
     합니다
    -0.06
    POSITIVE LOGITS
     appellate
    0.07
    ()._
    0.07
    .Resize
    0.07
     brokerage
    0.07
    ressive
    0.06
     correction
    0.06
     CrossAxisAlignment
    0.06
    raison
    0.06
    NotExist
    0.06
    -factor
    0.06
    Activations Density 0.000%

    No Known Activations