© 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. 124761
    Prev
    Next
    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash

    The neuron flags tokens in questions that ask what a word or pronoun refers to (e.g. “What does ‘it’ refer to?”).

    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
     Warwick
    -0.07
     careg
    -0.06
     �
    -0.06
     upfront
    -0.06
    <>("
    -0.06
     rallied
    -0.06
    (cljs
    -0.06
     İh
    -0.06
     everyday
    -0.06
    .ToTable
    -0.06
    POSITIVE LOGITS
    Unlock
    0.07
    dma
    0.07
    Contents
    0.06
     disparity
    0.06
    [frame
    0.06
    /web
    0.06
    뢰
    0.06
    دری
    0.06
    BER
    0.06
     essa
    0.06
    Activations Density 0.208%

    No Known Activations