© 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. 127042
    Prev
    Next
    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash

    This neuron detects reader‐engagement prompts—phrases that invite or ask the audience to share their thoughts (e.g. “Let us know… in the comments”).

    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
     podmín
    -0.06
    弄
    -0.06
     глуб
    -0.06
    	vo
    -0.06
    	all
    -0.06
    	dfs
    -0.06
    CallBack
    -0.06
     μό
    -0.06
    sprite
    -0.05
    Lord
    -0.05
    POSITIVE LOGITS
     Ä
    0.07
    _DURATION
    0.07
     Spicer
    0.07
     Aboriginal
    0.06
     supra
    0.06
     sturdy
    0.06
    iyor
    0.06
     Lup
    0.06
     Tem
    0.06
     máu
    0.06
    Activations Density 0.008%

    No Known Activations