© 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
    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. 126787
    Prev
    Next
    INDEX
    Explanations

    storage

    np_max-act · gemini-2.0-flash

    The neuron detects references to storage and shelving solutions—i.e. discussion of organizing space with shelves, bins, cabinets, and similar storage elements.

    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
     Trends
    -0.07
    _IMPL
    -0.07
     tags
    -0.07
     February
    -0.07
     March
    -0.07
     wars
    -0.06
     June
    -0.06
     Pixel
    -0.06
     Phys
    -0.06
     stems
    -0.06
    POSITIVE LOGITS
     minutos
    0.07
    ******/
    0.07
     pracovní
    0.06
     làn
    0.06
     nackte
    0.06
     nosso
    0.06
     玩家
    0.06
    場合
    0.06
    MODULE
    0.06
    .Btn
    0.06
    Activations Density 0.023%

    No Known Activations