© 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. 88233
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Negative Logits
    project
    -0.07
     �
    -0.06
     PROFITS
    -0.06
     discrepancies
    -0.06
     tink
    -0.06
     offended
    -0.06
     finding
    -0.06
     exploited
    -0.06
     Hancock
    -0.06
     nueva
    -0.06
    POSITIVE LOGITS
    SuppressWarnings
    0.06
     insurg
    0.06
    intestinal
    0.06
    0.06
    
    0.06
    =function
    0.06
    (bt
    0.06
    _intervals
    0.06
    iven
    0.06
    开始
    0.06
    Activations Density 0.000%
    No Known Activations