© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22468
    Prev
    Next
    INDEX
    Explanations

    JWT

    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
    Not in Any Lists

    No Comments

    Negative Logits
     سیم
    -0.07
     λειτουργ
    -0.06
     رسول
    -0.06
     Boston
    -0.06
    čast
    -0.06
     تغییر
    -0.06
     anybody
    -0.06
    .AsyncTask
    -0.06
     sis
    -0.06
     servisi
    -0.06
    POSITIVE LOGITS
     JWT
    0.11
     Jwt
    0.10
    jwt
    0.10
     jwt
    0.10
    Jwt
    0.10
    .JWT
    0.09
    wt
    0.07
    JWT
    0.07
    _jwt
    0.07
    	j
    0.07
    Activations Density 0.001%

    No Known Activations