© 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. 109184
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron activates on specific technical component nouns (e.g. names of mechanical parts or hardware elements).

    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
     Друг
    -0.07
    persist
    -0.07
    Workbook
    -0.06
    ارج
    -0.06
     अवध
    -0.06
    歩
    -0.06
    Pragma
    -0.06
    _popup
    -0.06
    interrupt
    -0.06
    -entry
    -0.06
    POSITIVE LOGITS
     Frm
    0.06
     offers
    0.06
    (screen
    0.06
     chce
    0.06
     な
    0.06
    =in
    0.06
    �
    0.06
    +F
    0.06
     frm
    0.06
     ссыл
    0.06
    Activations Density 0.105%

    No Known Activations