© 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. 44155
    Prev
    Next
    INDEX
    Explanations

    communes in France

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “communes” (as in the Wikipedia category or heading “Communes of …”), i.e. labels indicating French municipalities.

    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
     Pictures
    -0.07
    _Play
    -0.07
    Encryption
    -0.07
    ió
    -0.06
    Wy
    -0.06
    kernel
    -0.06
    Mel
    -0.06
     gears
    -0.06
    	fire
    -0.06
    cards
    -0.06
    POSITIVE LOGITS
     suis
    0.06
     Europeans
    0.06
     ніби
    0.06
     داشت
    0.06
     inauguration
    0.06
    _TOO
    0.06
    ua
    0.06
    =batch
    0.06
    wheel
    0.06
    IAM
    0.06
    Activations Density 0.008%

    No Known Activations