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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121835
    Prev
    Next
    INDEX
    Explanations

    embassies and consulates

    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
     Africa
    -0.06
     detective
    -0.06
    Ack
    -0.06
     buff
    -0.06
     SMART
    -0.06
     urban
    -0.06
    访
    -0.06
     band
    -0.06
     تو
    -0.06
     chast
    -0.06
    POSITIVE LOGITS
     consulate
    0.24
    ulate
    0.11
     Cons
    0.10
     Embassy
    0.08
     consul
    0.07
    ulates
    0.07
    ate
    0.07
     embassy
    0.06
     meme
    0.06
    Ann
    0.06
    Activations Density 0.003%

    No Known Activations