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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 79831
    Prev
    Next
    INDEX
    Explanations

    visa

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一定
    -0.07
     UIP
    -0.07
     лікар
    -0.06
    438
    -0.06
    amp
    -0.06
     golf
    -0.06
     NST
    -0.06
    _hd
    -0.06
    �
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     visa
    0.09
     Visa
    0.09
     lå
    0.07
     immigration
    0.07
    Concurrency
    0.06
     scheme
    0.06
    visa
    0.06
     Scheme
    0.06
     verdi
    0.06
     bid
    0.06
    Activations Density 0.002%

    No Known Activations