© 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. 7869
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    This neuron activates on words that signal a definitional or explanatory prompt—especially in “what does … mean” or “making a …” style phrases.

    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
     виник
    -0.07
    administration
    -0.07
    Banner
    -0.06
    _PLUGIN
    -0.06
    events
    -0.06
     Bols
    -0.06
    віль
    -0.06
    ентами
    -0.06
    exclude
    -0.06
    _UTF
    -0.06
    POSITIVE LOGITS
    头
    0.07
    一個
    0.06
     začátku
    0.06
     Pero
    0.06
     TextView
    0.06
    Please
    0.06
    .commons
    0.06
    (att
    0.06
    (currency
    0.06
     foundation
    0.06
    Activations Density 0.214%

    No Known Activations