Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 57395
    Prev
    Next
    INDEX
    Explanations

    dotenv

    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
    اذ
    -0.07
    Band
    -0.06
    ud
    -0.06
    there
    -0.06
     Balance
    -0.06
    Migration
    -0.06
    itin
    -0.06
    eron
    -0.06
    liquid
    -0.06
    ec
    -0.06
    POSITIVE LOGITS
     ihtiyaç
    0.08
    HasForeignKey
    0.07
    �
    0.07
     ;;^
    0.07
    inoa
    0.07
     swift
    0.06
    CHandle
    0.06
    ('/:
    0.06
     CLLocationCoordinate
    0.06
     реш
    0.06
    Activations Density 0.048%

    No Known Activations