© 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. 44808
    Prev
    Next
    INDEX
    Explanations

    Object

    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
    /nginx
    -0.07
     Télé
    -0.07
    ्ध
    -0.07
    -hooks
    -0.07
     '_',
    -0.06
    	Title
    -0.06
     fright
    -0.06
     moon
    -0.06
     FormData
    -0.06
     wife
    -0.06
    POSITIVE LOGITS
     materially
    0.06
     brasile
    0.06
     elderly
    0.06
    [item
    0.06
    らない
    0.06
     높은
    0.06
    Combined
    0.06
    (fill
    0.06
     директор
    0.06
     fax
    0.06
    Activations Density 0.028%

    No Known Activations