© 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. 104893
    Prev
    Next
    INDEX
    Explanations

    case number

    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
    _MSG
    -0.07
    alığı
    -0.06
     apologies
    -0.06
     lety
    -0.06
     ├──
    -0.06
     다양
    -0.06
    聘
    -0.06
    _DIM
    -0.06
    ارا
    -0.06
    TreeView
    -0.06
    POSITIVE LOGITS
     Elastic
    0.06
     benefiting
    0.06
     bli
    0.06
     Idle
    0.06
    ando
    0.06
     glyc
    0.06
    ogenerated
    0.06
     unders
    0.06
     subtitle
    0.06
     armor
    0.06
    Activations Density 0.012%

    No Known Activations