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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 104308
    Prev
    Next
    INDEX
    Explanations

    #:

    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
    	root
    -0.08
     (('
    -0.07
    	dest
    -0.07
    876
    -0.07
     někdo
    -0.06
     odbor
    -0.06
    908
    -0.06
     ovšem
    -0.06
     válido
    -0.06
    Reservation
    -0.06
    POSITIVE LOGITS
    ню
    0.07
    mark
    0.07
     فراو
    0.06
    раниц
    0.06
    اعية
    0.06
     нескольких
    0.06
    |:
    0.06
    มหานคร
    0.06
     financially
    0.06
    _toolbar
    0.06
    Activations Density 0.001%

    No Known Activations