© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89617
    Prev
    Next
    INDEX
    Explanations

    accompanying

    np_max-act · gemini-2.0-flash

    This neuron detects the word “accompanying” (as in “the accompanying X”), marking references to supplemental or related materials.

    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
    .\"
    -0.07
    (background
    -0.06
    cname
    -0.06
     vur
    -0.06
    ัช
    -0.06
     Chern
    -0.06
     newspapers
    -0.06
    WindowText
    -0.06
    ITableView
    -0.06
     "\\"
    -0.06
    POSITIVE LOGITS
    ierge
    0.07
    ordo
    0.07
    *scale
    0.06
     mutex
    0.06
    pink
    0.06
    asco
    0.06
    	img
    0.06
    longrightarrow
    0.06
    ічний
    0.06
     установ
    0.06
    Activations Density 0.008%

    No Known Activations