© 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. 15-RESID-POST-AA
    11. 92573
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash

    The neuron detects auxiliary verbs (forms of "be" and "have") used in continuous or perfect verb constructions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (Graphics
    -0.07
     हर
    -0.06
    	scroll
    -0.06
     GeForce
    -0.06
    ्ड
    -0.06
    Cookies
    -0.06
    raphics
    -0.06
    '",↵
    -0.06
    ethe
    -0.06
    ким
    -0.06
    POSITIVE LOGITS
    \D
    0.07
     �
    0.07
    StackNavigator
    0.07
    -custom
    0.06
    .Signal
    0.06
    VertexUvs
    0.06
    /report
    0.06
    ्यप
    0.06
    _WM
    0.06
    organ
    0.06
    Activations Density 0.080%

    No Known Activations