© 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. 51812
    Prev
    Next
    INDEX
    Explanations

    :

    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
     Intelligent
    -0.06
    梨
    -0.06
    ーパ
    -0.06
    .flatMap
    -0.06
    ेस
    -0.06
    樹
    -0.06
     reactive
    -0.06
    Trust
    -0.06
     yOffset
    -0.06
     tre
    -0.06
    POSITIVE LOGITS
     campaign
    0.07
     face
    0.07
     produits
    0.06
     etmek
    0.06
     altura
    0.06
     mensagem
    0.06
     Soldiers
    0.06
    公
    0.06
     uppercase
    0.06
    =f
    0.06
    Activations Density 0.084%

    No Known Activations