© 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. 64815
    Prev
    Next
    INDEX
    Explanations

    button states

    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
    unks
    -0.08
    nty
    -0.07
     psychologically
    -0.07
     янва
    -0.06
     disco
    -0.06
     waypoints
    -0.06
    actively
    -0.06
     Vital
    -0.06
     및
    -0.06
     constit
    -0.06
    POSITIVE LOGITS
    ARSER
    0.07
     nghiên
    0.07
    avatars
    0.06
     ()->
    0.06
     hesitant
    0.06
     "~/
    0.06
    ισε
    0.06
     Giul
    0.06
    _.
    0.06
    angler
    0.06
    Activations Density 0.011%

    No Known Activations