© 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. 73798
    Prev
    Next
    INDEX
    Explanations

    city

    np_max-act · gemini-2.0-flash

    The neuron fires on the segmented pieces of Chinese place names (e.g. the “Y”, “anch”, “eng” tokens in “Yancheng”), effectively detecting mentions of the company’s city location.

    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
    Kal
    -0.07
    mitter
    -0.07
     superf
    -0.07
     ıs
    -0.06
     melted
    -0.06
     në
    -0.06
     Aires
    -0.06
     antes
    -0.06
    .handlers
    -0.06
     amendment
    -0.06
    POSITIVE LOGITS
    ิญญ
    0.07
     ".
    0.07
    	Q
    0.07
    ,value
    0.06
    #$
    0.06
     '`
    0.06
    ада
    0.06
     valley
    0.06
     cardboard
    0.06
    ODEV
    0.06
    Activations Density 0.030%

    No Known Activations