© 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. 56235
    Prev
    Next
    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash

    This neuron fires on website or page header greetings—phrases like “Welcome to our …” that introduce a site or section.

    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
    UILD
    -0.07
    Modes
    -0.07
    _CLIENT
    -0.07
     rowspan
    -0.06
    mongoose
    -0.06
     prefix
    -0.06
     volcanic
    -0.06
     Touch
    -0.06
     attack
    -0.06
     Poland
    -0.06
    POSITIVE LOGITS
    يير
    0.06
    ζει
    0.06
     ide
    0.06
    pick
    0.06
     Legislative
    0.06
    contres
    0.05
     i
    0.05
    urence
    0.05
    ozor
    0.05
    ;i
    0.05
    Activations Density 0.022%

    No Known Activations