© 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. 80569
    Prev
    Next
    INDEX
    Explanations

    tropes descriptions stories

    np_max-act · gemini-2.0-flash

    The neuron mainly detects named entities and other proper nouns—people, places, titles, dates, and similar capitalized or distinctive tokens.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    Bomb
    -0.07
    quote
    -0.07
    ERTICAL
    -0.07
     edited
    -0.06
    tempt
    -0.06
    ingredient
    -0.06
     COMP
    -0.06
     sanct
    -0.06
    flat
    -0.06
     reminder
    -0.06
    POSITIVE LOGITS
     расч
    0.07
     nebylo
    0.06
    $is
    0.06
     zza
    0.06
    =_('
    0.06
    '>{
    0.06
    対応
    0.06
    (UnmanagedType
    0.06
    .Environment
    0.06
    �
    0.06
    Activations Density 0.152%

    No Known Activations