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. 24056
    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
    tribution
    -0.07
    摘
    -0.06
    xing
    -0.06
    endment
    -0.06
    啦
    -0.06
     ک
    -0.06
    014
    -0.06
    loon
    -0.06
    lake
    -0.06
     JSGlobal
    -0.06
    POSITIVE LOGITS
     Fiber
    0.07
    虫
    0.07
    	Client
    0.07
     crafted
    0.06
     Northern
    0.06
     Investment
    0.06
     Tales
    0.06
     saw
    0.06
    Bob
    0.06
     came
    0.06
    Activations Density 0.005%

    No Known Activations