Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 128902
    Prev
    Next
    INDEX
    Explanations

    school parent organizations

    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
    YE
    -0.06
    sti
    -0.06
     yeni
    -0.06
     gridSize
    -0.06
    acb
    -0.06
     yapılacak
    -0.06
     cháy
    -0.06
    wan
    -0.06
     usernames
    -0.06
     limit
    -0.06
    POSITIVE LOGITS
    Nav
    0.06
     cognitive
    0.06
    чества
    0.06
    ΕΣ
    0.06
     Serge
    0.06
    лем
    0.06
    [System
    0.06
     Injectable
    0.06
     Vive
    0.06
    ibia
    0.06
    Activations Density 0.015%

    No Known Activations