© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85821
    Prev
    Next
    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash

    historical references and significant events related to specific places.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron chiefly activates on proper nouns denoting place names (towns, parks, rivers, etc.).

    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
     Ivan
    -0.08
    _CONTINUE
    -0.07
    ele
    -0.07
    896
    -0.07
     unfolds
    -0.07
     decis
    -0.07
    configuration
    -0.07
    gap
    -0.06
     Patton
    -0.06
     assignments
    -0.06
    POSITIVE LOGITS
     ilk
    0.06
    シー
    0.06
     weblog
    0.05
    _theta
    0.05
     comentario
    0.05
     Freed
    0.05
     pollutants
    0.05
     vyjád
    0.05
     dní
    0.05
     resil
    0.05
    Activations Density 0.068%

    No Known Activations