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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 79801
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
    časí
    -0.06
    %f
    -0.06
    ums
    -0.06
    jian
    -0.06
    compet
    -0.06
     trick
    -0.06
    잖
    -0.06
     coloring
    -0.06
    >,
    -0.06
     vc
    -0.06
    POSITIVE LOGITS
    DataProvider
    0.07
    โครงการ
    0.07
    OfBirth
    0.07
     инт
    0.06
     外部
    0.06
    	throws
    0.06
     ноября
    0.06
     lợi
    0.06
     MainActivity
    0.06
     thờ
    0.06
    Activations Density 2.435%

    No Known Activations