© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56169
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on programming identifiers in code examples (e.g. class/component names like “Inbox” or “New,” type names like “float”), marking tokens that look like code identifiers.

    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
     trickle
    -0.07
     mating
    -0.06
    odě
    -0.06
    .book
    -0.06
     rescue
    -0.06
     disks
    -0.06
     pouvoir
    -0.06
    測
    -0.06
     petit
    -0.06
     Susan
    -0.06
    POSITIVE LOGITS
     περιο
    0.07
    Entropy
    0.07
    -Петерб
    0.06
    ฟ
    0.06
     Gina
    0.06
    	image
    0.06
     HttpServlet
    0.06
     katıl
    0.06
     &);↵
    0.06
     Worce
    0.06
    Activations Density 0.030%

    No Known Activations