© 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. 76376
    Prev
    Next
    INDEX
    Explanations

    measurements

    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
     regularization
    -0.07
    cu
    -0.07
     stellen
    -0.07
    ぶ
    -0.07
     succès
    -0.06
    .ResponseWriter
    -0.06
    render
    -0.06
     oluştur
    -0.06
    DEM
    -0.06
    CO
    -0.06
    POSITIVE LOGITS
     rogue
    0.06
    ceased
    0.06
    524
    0.06
     gritty
    0.06
     '".$_
    0.06
     Donne
    0.06
     reconcile
    0.06
    ặp
    0.06
    ('.')
    0.06
     amid
    0.06
    Activations Density 0.013%

    No Known Activations