© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91492
    Prev
    Next
    INDEX
    Explanations

    Google

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the brand name “Google.”

    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
    recipe
    -0.07
    ourses
    -0.07
     Boards
    -0.07
    іт
    -0.07
     bake
    -0.06
     deserve
    -0.06
    avings
    -0.06
    macro
    -0.06
     bathrooms
    -0.06
    ident
    -0.06
    POSITIVE LOGITS
     Tesla
    0.07
    ений
    0.06
     Lemma
    0.06
    .Fatal
    0.06
    스를
    0.06
     slamming
    0.06
    ?v
    0.05
    ,x
    0.05
     Toyota
    0.05
     خدمات
    0.05
    Activations Density 0.007%

    No Known Activations