© 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. 19-RESID-POST-AA
    11. 111965
    Prev
    Next
    INDEX
    Explanations

    restaurants

    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
     mole
    -0.08
     dz
    -0.07
     bold
    -0.07
     Money
    -0.07
     Polic
    -0.07
    ัวอย
    -0.06
     ello
    -0.06
     negatives
    -0.06
     lie
    -0.06
     Volvo
    -0.06
    POSITIVE LOGITS
     restaurant
    0.08
     restaurants
    0.07
    ियल
    0.06
    atat
    0.06
     příč
    0.06
    .Minute
    0.06
    sole
    0.06
    .numberOfLines
    0.06
    :"
    0.06
     pause
    0.06
    Activations Density 0.023%

    No Known Activations