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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RESID-POST-AA
    11. 123290
    Prev
    Next
    INDEX
    Explanations

    democratic

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (&:
    -0.07
    !=
    -0.07
    [ix
    -0.06
     tsl
    -0.06
     اي
    -0.06
     avail
    -0.06
    іг
    -0.06
    وقيت
    -0.06
     Vanity
    -0.06
    lasyon
    -0.06
    POSITIVE LOGITS
     Democratic
    0.27
     democratic
    0.26
    Democratic
    0.22
    ocratic
    0.16
     democr
    0.12
    ocrats
    0.11
     Democrats
    0.10
     demok
    0.10
    民主
    0.09
    Democrats
    0.08
    Activations Density 0.004%

    No Known Activations