© 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. 23504
    Prev
    Next
    INDEX
    Explanations

    backslash

    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
    ROLL
    -0.07
    roll
    -0.07
     Higgins
    -0.07
    -point
    -0.07
    verse
    -0.07
     Rate
    -0.07
     Theft
    -0.06
     verg
    -0.06
     prove
    -0.06
    _mouse
    -0.06
    POSITIVE LOGITS
    「あ
    0.08
    sqlite
    0.07
     teşkil
    0.07
     Anadolu
    0.07
     Malay
    0.06
     Coastal
    0.06
    刘
    0.06
     영
    0.06
    .xy
    0.06
     respondsToSelector
    0.06
    Activations Density 0.006%

    No Known Activations