© 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. 93715
    Prev
    Next
    INDEX
    Explanations

    German

    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
     Av
    -0.06
     resisting
    -0.06
    Seeder
    -0.06
    bes
    -0.06
    first
    -0.06
    eller
    -0.06
    _intersection
    -0.06
    いう
    -0.06
    舰
    -0.06
     uc
    -0.06
    POSITIVE LOGITS
     kommt
    0.16
     kommen
    0.13
     bringen
    0.11
     komt
    0.09
     komen
    0.09
     kommer
    0.08
     bekommen
    0.08
    /oauth
    0.07
     bson
    0.07
     ovar
    0.06
    Activations Density 0.023%

    No Known Activations