© 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. 109491
    Prev
    Next
    INDEX
    Explanations

    western

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of “Western” (e.g., the Western United States) or the term “western” indicating that region.

    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
    _Utils
    -0.07
     broker
    -0.07
     Lazar
    -0.06
    міну
    -0.06
    ‌ش
    -0.06
                                                           
    -0.06
     cake
    -0.06
     NavBar
    -0.06
    طار
    -0.06
     Guil
    -0.06
    POSITIVE LOGITS
    ."</
    0.07
    ("/:
    0.07
     Western
    0.07
    Western
    0.07
     west
    0.06
     Afghanistan
    0.06
     qw
    0.06
    ?");↵
    0.06
    pets
    0.06
    void
    0.06
    Activations Density 0.004%

    No Known Activations