© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78095
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron is highly attuned to numeric literals (i.e. integer constants) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    macros related to manipulating and managing data in Excel spreadsheets.

    oai_token-act-pair · gpt-4o-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
    \Collection
    -0.07
    =}
    -0.06
    Ten
    -0.06
     krat
    -0.06
     flow
    -0.06
    .databind
    -0.06
    BootApplication
    -0.06
     xuống
    -0.06
     fluid
    -0.06
    WO
    -0.05
    POSITIVE LOGITS
    .about
    0.07
     tidak
    0.06
    а�
    0.06
    ンド
    0.06
    	JButton
    0.06
     Dummy
    0.06
     غر
    0.06
    ieme
    0.06
     відвід
    0.06
    引用
    0.06
    Activations Density 0.002%

    No Known Activations