© 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. 15-RESID-POST-AA
    11. 5840
    Prev
    Next
    INDEX
    Explanations

    Calculations and summations

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nome
    -0.07
     hizmet
    -0.07
     xo
    -0.07
     vrát
    -0.07
    umno
    -0.07
    ̉
    -0.06
    Empleado
    -0.06
    *cos
    -0.06
    	sig
    -0.06
     NSK
    -0.06
    POSITIVE LOGITS
    -ROM
    0.07
    .Categories
    0.06
     NOTES
    0.06
     Username
    0.06
    akin
    0.06
    ушка
    0.06
    طة
    0.06
    :int
    0.06
     الأن
    0.06
     Creator
    0.06
    Activations Density 0.017%

    No Known Activations