© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 47484
    Prev
    Next
    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash

    descriptions of specific cultural items and traditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    安
    -0.07
    ง
    -0.07
     δεδο
    -0.07
    تاب
    -0.06
    ані
    -0.06
    封
    -0.06
     tôi
    -0.06
    ]:↵↵↵
    -0.06
     Awakening
    -0.06
     uděl
    -0.06
    POSITIVE LOGITS
     ih
    0.07
    yc
    0.07
    YPE
    0.07
     gezocht
    0.07
     amid
    0.06
    PointCloud
    0.06
    sigmoid
    0.06
     Gov
    0.06
     チ
    0.06
     dilemma
    0.06
    Activations Density 0.013%

    No Known Activations