Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 93192
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ünü
    -0.07
     мис
    -0.07
    植
    -0.07
    <html
    -0.07
    からは
    -0.06
    (source
    -0.06
     memnun
    -0.06
    esti
    -0.06
    issa
    -0.06
    บ
    -0.06
    POSITIVE LOGITS
     Classifier
    0.07
     foc
    0.07
     œ
    0.06
    administrator
    0.06
    134
    0.06
     wishlist
    0.06
    ','$
    0.06
    235
    0.06
     restructuring
    0.06
    Transfer
    0.06
    Activations Density 0.042%

    No Known Activations