© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126085
    Prev
    Next
    INDEX
    Explanations

    quotes and sayings

    np_max-act · gemini-2.0-flash

    This neuron detects the “atoms” joke—specifically the phrase “scientists don’t trust atoms … because they make up everything.”

    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
    ToLower
    -0.07
    ertility
    -0.06
     dtype
    -0.06
    -Requested
    -0.06
    订单
    -0.06
    (inplace
    -0.06
     teeth
    -0.06
     pristine
    -0.06
    ERC
    -0.06
     مون
    -0.06
    POSITIVE LOGITS
    .di
    0.07
     Cousins
    0.06
     Carolyn
    0.06
    Trait
    0.06
    -members
    0.06
    ANGE
    0.06
    uci
    0.06
    anooga
    0.06
    knife
    0.06
    рок
    0.06
    Activations Density 0.002%

    No Known Activations