© 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. 24353
    Prev
    Next
    INDEX
    Explanations

    debug

    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
    aket
    -0.08
    621
    -0.07
     Consort
    -0.07
    706
    -0.07
    -circle
    -0.07
     EN
    -0.07
     کاهش
    -0.07
     ku
    -0.07
     Cartesian
    -0.06
    377
    -0.06
    POSITIVE LOGITS
    debug
    0.08
     Bugs
    0.07
    ska
    0.07
    Debug
    0.07
     agendas
    0.07
    .Logf
    0.07
    .impl
    0.07
    ddd
    0.07
     debug
    0.06
     bug
    0.06
    Activations Density 0.008%

    No Known Activations