© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102607
    Prev
    Next
    INDEX
    Explanations

    could

    np_max-act · gemini-2.0-flash

    The neuron is a detector for interrogative question phrasing, particularly firing on WH-question words and structures that signal a user is asking numbered or “What/How/Why” style questions.

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

    situations that involve waiting or delayed gratification in everyday contexts.

    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
    itures
    -0.06
    scalar
    -0.06
     Granny
    -0.06
    money
    -0.06
    (in
    -0.06
    (prod
    -0.06
     Grat
    -0.06
    説
    -0.06
    (Socket
    -0.06
    char
    -0.06
    POSITIVE LOGITS
    getConnection
    0.07
     TRANSACTION
    0.06
    Kon
    0.06
    她们
    0.06
     Billing
    0.06
     bude
    0.06
    Ali
    0.06
    strip
    0.06
    　　　　　　　　
    0.06
     migrations
    0.06
    Activations Density 0.049%

    No Known Activations