© 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. 19-RESID-POST-AA
    11. 31636
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    initWith
    -0.07
     regained
    -0.06
    可以
    -0.06
    Ever
    -0.06
     initWith
    -0.06
    .Tab
    -0.06
    ysqli
    -0.06
     Marl
    -0.06
    addColumn
    -0.06
     kanıt
    -0.06
    POSITIVE LOGITS
    _COST
    0.07
    egrate
    0.07
    �
    0.07
     нав
    0.07
     unfore
    0.06
    (Local
    0.06
    Retry
    0.06
     TB
    0.06
     saline
    0.06
    σίας
    0.06
    Activations Density 0.000%

    No Known Activations