© 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. 109640
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on the infinitive “to” when used in instructional or requirement statements (e.g. “need to import,” “to handle,” “to create”).

    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
    Spark
    -0.07
     startups
    -0.07
    _READY
    -0.06
    -issue
    -0.06
    Obviously
    -0.06
     Boulevard
    -0.06
     Wordpress
    -0.06
    prestashop
    -0.06
    _attach
    -0.06
    (prev
    -0.06
    POSITIVE LOGITS
     eject
    0.07
    ैठक
    0.07
     warto
    0.06
     payable
    0.06
    ()
↵
↵
    0.06
     ($.
    0.06
     tık
    0.06
     може
    0.06
    ??↵↵
    0.06
    079
    0.06
    Activations Density 0.053%

    No Known Activations