© 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. 19-RESID-POST-AA
    11. 109448
    Prev
    Next
    INDEX
    Explanations

    understanding something

    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
    Not in Any Lists

    No Comments

    Negative Logits
    сть
    -0.07
     experience
    -0.06
    .feed
    -0.06
     tồn
    -0.06
     less
    -0.06
     Jar
    -0.06
     Tire
    -0.06
    cock
    -0.06
    _row
    -0.06
     Feed
    -0.06
    POSITIVE LOGITS
    entarios
    0.07
     GNOME
    0.07
     recreate
    0.06
     Tells
    0.06
    -important
    0.06
     giy
    0.06
     ■
    0.06
    .anim
    0.06
    046
    0.06
     sensing
    0.06
    Activations Density 0.017%

    No Known Activations