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. 7-RESID-POST-AA
    6. 111730
    Prev
    Next
    INDEX
    Explanations

    provoking a response

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fiesta
    -0.07
    	Time
    -0.07
    sanız
    -0.06
    فق
    -0.06
    國
    -0.06
    493
    -0.06
    inston
    -0.06
     samot
    -0.06
     ノ
    -0.06
     retaliation
    -0.06
    POSITIVE LOGITS
     دانشگاه
    0.07
    了解
    0.06
    _DB
    0.06
    比較
    0.06
     จ
    0.06
    くれ
    0.06
     OW
    0.06
     contrast
    0.06
    lio
    0.06
    Produ
    0.06
    Activations Density 0.188%

    No Known Activations