© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109697
    Prev
    Next
    INDEX
    Explanations

    shirts

    np_max-act · gemini-2.0-flash

    The neuron detects tokens related to print-on-demand apparel—especially T-shirts and similar merchandise.

    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
    ollectors
    -0.06
     disciples
    -0.06
     eleştir
    -0.06
    ocide
    -0.06
     уп
    -0.06
    扣
    -0.06
     ship
    -0.06
     Matchers
    -0.06
    (cat
    -0.06
     vyšší
    -0.06
    POSITIVE LOGITS
    getString
    0.07
     STOCK
    0.07
    =device
    0.07
    окрем
    0.07
     Lt
    0.07
    ')}}">
    0.06
     DIY
    0.06
     --------------------------------
    0.06
     united
    0.06
     setInterval
    0.06
    Activations Density 0.022%

    No Known Activations