© 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. 7-RESID-POST-AA
    11. 55974
    Prev
    Next
    INDEX
    Explanations

    refuse

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     آیا
    -0.06
    -nil
    -0.06
     hott
    -0.06
    istik
    -0.06
    ères
    -0.06
     свидетель
    -0.06
     chứng
    -0.06
     zám
    -0.06
     сост
    -0.06
    ัปดาห
    -0.06
    POSITIVE LOGITS
     refused
    0.15
     refuse
    0.13
     refuses
    0.13
     refusing
    0.11
     refusal
    0.09
     Ref
    0.09
     refund
    0.08
    buf
    0.08
     відмов
    0.08
    prm
    0.07
    Activations Density 0.006%

    No Known Activations