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. 11-RESID-POST-AA
    6. 22045
    Prev
    Next
    INDEX
    Explanations

    debt

    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
     Allen
    -0.08
     Kawasaki
    -0.07
     uydu
    -0.07
     Wan
    -0.07
    рава
    -0.07
     Roller
    -0.07
     microscopic
    -0.07
    rosse
    -0.07
     Rounds
    -0.07
    よね
    -0.06
    POSITIVE LOGITS
     debt
    0.14
     Debt
    0.13
     debts
    0.10
     dept
    0.07
     becomes
    0.07
     nợ
    0.07
     at
    0.06
     indebted
    0.06
     Deborah
    0.06
     creditor
    0.06
    Activations Density 0.005%

    No Known Activations