© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29496
    Prev
    Next
    INDEX
    Explanations

    Advice and warnings

    np_max-act · gemini-2.0-flash

    The neuron flags tokens in contexts warning about or describing harmful, inappropriate, or unsafe behaviors.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    (Canvas
    -0.08
    ár
    -0.06
     ultimately
    -0.06
    getDrawable
    -0.06
    	page
    -0.06
     TreeNode
    -0.06
    borg
    -0.06
    <table
    -0.06
     brands
    -0.06
     cryptocurrencies
    -0.06
    POSITIVE LOGITS
     교육
    0.07
     батар
    0.06
     انرژی
    0.06
     परम
    0.06
     cro
    0.06
    _;
↵
    0.06
     reopen
    0.06
    [class
    0.06
    láv
    0.06
     MAKE
    0.06
    Activations Density 0.040%

    No Known Activations