© 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. 37945
    Prev
    Next
    INDEX
    Explanations

    wide

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “wide range of,” especially picking up the word “wide” in contexts like “a wide range of.”

    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
     світі
    -0.06
     здійс
    -0.06
    	cb
    -0.06
    -tools
    -0.06
    _helpers
    -0.06
    露出
    -0.06
     nhựa
    -0.06
    ζό
    -0.06
     пош
    -0.06
     отвер
    -0.06
    POSITIVE LOGITS
    BILL
    0.07
     vowed
    0.07
     acknowledged
    0.07
     calendar
    0.06
     entityManager
    0.06
    _codigo
    0.06
    /Sub
    0.06
     noisy
    0.06
    γγ
    0.06
     novel
    0.06
    Activations Density 0.013%

    No Known Activations