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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 53939
    Prev
    Next
    INDEX
    Explanations

    SOR

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colo
    -0.06
    úp
    -0.06
    PER
    -0.06
     JNICALL
    -0.06
     Cary
    -0.06
    col
    -0.06
     Ru
    -0.06
    ламент
    -0.06
     справа
    -0.06
    убли
    -0.06
    POSITIVE LOGITS
    	Destroy
    0.07
     مدیر
    0.07
     NETWORK
    0.07
    stdlib
    0.07
    าจ
    0.07
    Scalars
    0.06
    -Headers
    0.06
     image
    0.06
     Cisco
    0.06
     images
    0.06
    Activations Density 0.003%

    No Known Activations