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. 119411
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ा-
    -0.07
    -he
    -0.07
     Pere
    -0.06
    getRoot
    -0.06
     mỗi
    -0.06
    nutím
    -0.06
    jeme
    -0.06
    :`~
    -0.06
     apologized
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     withholding
    0.06
    MODULE
    0.06
     kavram
    0.06
     orderly
    0.06
    (INVOKE
    0.06
     чай
    0.06
    folders
    0.06
     Hö
    0.06
    						   
    0.06
    commons
    0.06
    Activations Density 0.011%

    No Known Activations