© 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. 25399
    Prev
    Next
    INDEX
    Explanations

    error/warning

    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
    lrt
    -0.07
     tide
    -0.07
     crust
    -0.07
    621
    -0.07
     Ax
    -0.06
     homes
    -0.06
    where
    -0.06
     سیم
    -0.06
     buddy
    -0.06
    .Patient
    -0.06
    POSITIVE LOGITS
    (prog
    0.07
     kaliteli
    0.06
     activist
    0.06
    fef
    0.06
    arton
    0.06
     boz
    0.06
    (())↵
    0.06
     Hollande
    0.05
     只
    0.05
    贵
    0.05
    Activations Density 0.017%

    No Known Activations