© 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. 128571
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on the list‐intro phrase “including,” i.e. words that introduce examples of product ranges.

    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
     Heaven
    -0.06
    .time
    -0.06
    variably
    -0.06
    ework
    -0.06
     overpower
    -0.06
     Sou
    -0.06
     SQUARE
    -0.06
     meisje
    -0.06
    Alarm
    -0.06
    .is
    -0.06
    POSITIVE LOGITS
    цієн
    0.08
     indian
    0.07
    
    0.06
     بالإ
    0.06
     gameplay
    0.06
    EDIATE
    0.06
    ้องการ
    0.06
     演
    0.06
    barcode
    0.06
    ครบ
    0.06
    Activations Density 0.050%

    No Known Activations