© 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. 73555
    Prev
    Next
    INDEX
    Explanations

    connection

    np_max-act · gemini-2.0-flash

    the neuron selectively activates on occurrences of the identifier “connection” (especially in types, variables, and methods related to a Connection object).

    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
     至
    -0.06
     došlo
    -0.06
    또
    -0.06
     WEIGHT
    -0.06
    об
    -0.06
     Spa
    -0.06
    其实
    -0.06
    _New
    -0.06
     Assange
    -0.06
     pill
    -0.06
    POSITIVE LOGITS
    	constructor
    0.06
    /service
    0.06
    -meta
    0.06
     ''){↵
    0.06
    ленный
    0.06
     constructor
    0.06
     castle
    0.06
     china
    0.06
    ленно
    0.06
    FACT
    0.06
    Activations Density 0.024%

    No Known Activations