© 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. 92465
    Prev
    Next
    INDEX
    Explanations

    typical

    np_max-act · gemini-2.0-flash

    This neuron detects generalizing adverbs (e.g. typically, generally, usually, mostly) that qualify statements as normal or expected.

    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
     liberty
    -0.07
    plist
    -0.06
     Nam
    -0.06
    //
    -0.06
    academic
    -0.06
     approach
    -0.06
     succeeding
    -0.06
     POLITICO
    -0.06
     люди
    -0.06
     speeches
    -0.06
    POSITIVE LOGITS
    .Len
    0.07
     RDD
    0.06
     akka
    0.06
    .Field
    0.06
    尽管
    0.06
    	actor
    0.06
    .removeAttribute
    0.06
    .Gen
    0.06
     gerçekleştir
    0.06
    $args
    0.06
    Activations Density 0.054%

    No Known Activations