© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59292
    Prev
    Next
    INDEX
    Explanations

    Ref

    np_max-act · gemini-2.0-flash

    The neuron responds to structural markers of section headings in the paper—e.g. the “###” subsection tags and “Ref” in “Refinement.”

    oai_token-act-pair · o4-mini
    Triggered by @xinyanhu8

    elements related to crystal structures and their data parameters.

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     hồng
    -0.07
    upertino
    -0.06
    AspNet
    -0.06
    .scrollHeight
    -0.06
    \Foundation
    -0.06
    .Score
    -0.06
    薄
    -0.06
    Storage
    -0.06
    issing
    -0.06
    DialogContent
    -0.06
    POSITIVE LOGITS
     مو
    0.07
     third
    0.06
     почина
    0.06
     momento
    0.06
    <Comment
    0.06
    	TRACE
    0.06
     lineup
    0.06
     modelo
    0.06
     настоя
    0.06
     вещества
    0.06
    Activations Density 0.000%

    No Known Activations