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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7667
    Prev
    Next
    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash

    This neuron detects the closing invitation phrase “let me know if you have any questions.”

    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
    ४
    -0.07
    (suffix
    -0.07
    ıf
    -0.07
    Does
    -0.06
    endors
    -0.06
     Drag
    -0.06
     LENG
    -0.06
    Study
    -0.06
    〔
    -0.06
     debtor
    -0.06
    POSITIVE LOGITS
     pokemon
    0.07
     Squad
    0.07
     Cellular
    0.06
     Transmission
    0.06
     tüket
    0.06
     Alam
    0.06
     Пов
    0.06
     wxDefault
    0.06
     UPS
    0.06
    лан
    0.06
    Activations Density 0.007%

    No Known Activations