© 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. 73732
    Prev
    Next
    INDEX
    Explanations

    US

    np_max-act · gemini-2.0-flash

    The neuron fires in response to the token “US,” effectively detecting mentions of the United States abbreviation.

    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
    ini
    -0.08
    INI
    -0.07
    ango
    -0.07
     Richards
    -0.07
     Dani
    -0.06
     magn
    -0.06
    enga
    -0.06
     Oyun
    -0.06
    ainter
    -0.06
    arp
    -0.06
    POSITIVE LOGITS
     US
    0.18
    US
    0.14
    -US
    0.13
    .US
    0.10
    /us
    0.10
     USA
    0.09
     USS
    0.09
     EU
    0.09
     States
    0.09
     UK
    0.08
    Activations Density 0.066%

    No Known Activations