© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 829
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially numbers with decimal points (e.g. “1.42”, “0.27”, “18.68”)—i.e. it’s detecting the appearance of decimal‐formatted numerical values.

    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
    -legged
    -0.06
     çat
    -0.06
    ibi
    -0.06
     lip
    -0.06
     Balance
    -0.06
     Telecom
    -0.06
     widget
    -0.06
    	left
    -0.06
     Seat
    -0.06
    ën
    -0.06
    POSITIVE LOGITS
    ={[↵
    0.07
     confl
    0.06
     참
    0.06
     �
    0.06
     combineReducers
    0.06
    .setCursor
    0.06
    _PO
    0.06
    _book
    0.06
    еся
    0.06
     earned
    0.06
    Activations Density 0.017%

    No Known Activations