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. 3-RESID-POST-AA
    6. 94856
    Prev
    Next
    INDEX
    Explanations

    culture

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     انت
    -0.06
     fst
    -0.06
     />↵
    -0.06
    /add
    -0.06
     raining
    -0.06
     운영
    -0.06
     nod
    -0.06
     在
    -0.06
    ...)↵
    -0.06
     unp
    -0.06
    POSITIVE LOGITS
     Kotlin
    0.07
     Serialize
    0.07
     projektu
    0.06
    .not
    0.06
     proceeds
    0.06
    (Student
    0.06
    _LIBRARY
    0.06
    출장마사지
    0.06
    .Unique
    0.06
    bris
    0.06
    Activations Density 0.073%

    No Known Activations