© 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. 100147
    Prev
    Next
    INDEX
    Explanations

    gendered people

    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
     prophecy
    -0.07
     quoting
    -0.07
     weapon
    -0.06
     Inputs
    -0.06
    ürn
    -0.06
    undle
    -0.06
    Spring
    -0.06
    щими
    -0.06
    ²
    -0.06
     dell
    -0.06
    POSITIVE LOGITS
    },
    0.07
     manip
    0.07
    _cliente
    0.06
     hlav
    0.06
    ีอย
    0.06
     واقع
    0.06
     htonl
    0.06
     металли
    0.06
    ])
    0.06
    alığı
    0.06
    Activations Density 0.028%

    No Known Activations