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. 11-RESID-POST-AA
    6. 78815
    Prev
    Next
    INDEX
    Explanations

    geography and weather

    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
    avored
    -0.07
    assets
    -0.07
    BIT
    -0.07
     realize
    -0.07
     crazy
    -0.07
     Hundreds
    -0.06
     btn
    -0.06
     prove
    -0.06
    URN
    -0.06
    bitmap
    -0.06
    POSITIVE LOGITS
     використовувати
    0.07
     ör
    0.07
     беременности
    0.06
    (ll
    0.06
    IODevice
    0.06
     zeměděl
    0.06
     δημιουργ
    0.06
     RH
    0.06
     udál
    0.06
     """.
    0.06
    Activations Density 0.313%

    No Known Activations