© 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. 43003
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐related tokens—language keywords, import paths, class/type names, and other 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
     CompletableFuture
    -0.06
    acceptable
    -0.06
    _Syntax
    -0.06
    *cos
    -0.06
     buddies
    -0.06
     名無しさん
    -0.05
    Intensity
    -0.05
     zonder
    -0.05
    eel
    -0.05
    hy
    -0.05
    POSITIVE LOGITS
     Türkiye
    0.08
    -Cal
    0.07
     也
    0.07
     पक
    0.06
     Alexa
    0.06
     Morse
    0.06
    /world
    0.06
     Agency
    0.06
    _TOP
    0.06
    ่านมา
    0.06
    Activations Density 0.108%

    No Known Activations