© 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. 7-RESID-POST-AA
    11. 79821
    Prev
    Next
    INDEX
    Explanations

    en

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    bubble
    -0.06
    ์กร
    -0.06
    +W
    -0.06
    forward
    -0.06
    (customer
    -0.06
     padr
    -0.06
    _hard
    -0.06
    clientId
    -0.06
    _free
    -0.06
    .gsub
    -0.06
    POSITIVE LOGITS
    วม
    0.07
    tplib
    0.06
    園
    0.06
     chờ
    0.06
     riot
    0.06
     downt
    0.06
     трех
    0.06
     gim
    0.06
    دم
    0.06
    ーフ
    0.06
    Activations Density 0.001%

    No Known Activations