© 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. 11-RESID-POST-AA
    11. 35306
    Prev
    Next
    INDEX
    Explanations

    Prepositions

    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
     attacker
    -0.08
    。他
    -0.07
     barr
    -0.07
     aston
    -0.07
     alt
    -0.06
     الميلاد
    -0.06
     fortune
    -0.06
     Dagger
    -0.06
     ký
    -0.06
     Bast
    -0.06
    POSITIVE LOGITS
     пром
    0.07
    Compra
    0.06
    ierarchical
    0.06
    ��글
    0.06
    :event
    0.06
    ]';↵
    0.06
    xin
    0.06
     QHBoxLayout
    0.06
     Entity
    0.06
     піс
    0.06
    Activations Density 0.006%

    No Known Activations