© 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. 92010
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of numeric quantities (numbers and spelled-out counts) in the text.

    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
     Washington
    -0.07
     birthday
    -0.06
     hipp
    -0.06
     playoffs
    -0.06
    anan
    -0.06
     راه
    -0.06
    amenti
    -0.06
     layouts
    -0.06
     birthdays
    -0.06
    rar
    -0.06
    POSITIVE LOGITS
     +++
    0.07
    Essay
    0.07
    (Stack
    0.07
    _eps
    0.07
    pricing
    0.06
     erased
    0.06
     поль
    0.06
     Зап
    0.06
     maxim
    0.06
     INT
    0.06
    Activations Density 0.098%

    No Known Activations