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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 93616
    Prev
    Next
    INDEX
    Explanations

    travel and tourism

    np_max-act · gemini-2.0-flash

    references to real estate and property-related information.

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

    The main thing this neuron does is detect parts of geographic place names (city, region, or landmark names).

    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
     vessels
    -0.07
     mitochondrial
    -0.07
     comforting
    -0.06
    hello
    -0.06
    elled
    -0.06
    itura
    -0.06
     Rim
    -0.06
     intro
    -0.06
    _Address
    -0.06
     POINT
    -0.06
    POSITIVE LOGITS
     '',
    ↵
    0.07
     tinha
    0.07
     )
    ↵
    ↵
    0.06
    ([]*
    0.06
    ,[
    0.06
    EncodingException
    0.06
    КТ
    0.06
     �
    0.06
     Menschen
    0.06
    (Status
    0.06
    Activations Density 0.033%

    No Known Activations