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. 19-RESID-POST-AA
    6. 99226
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous information

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trị
    -0.07
    
    -0.06
     pretending
    -0.06
     음악
    -0.06
    まった
    -0.06
    合
    -0.06
     Fighters
    -0.06
     verilen
    -0.06
    (found
    -0.06
    ็นท
    -0.06
    POSITIVE LOGITS
     ART
    0.06
     publications
    0.06
    és
    0.06
    <Result
    0.06
     graduation
    0.06
    _STOCK
    0.06
    设施
    0.06
     INV
    0.06
    υν
    0.06
    Md
    0.06
    Activations Density 0.248%

    No Known Activations