© 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. 92573
    Prev
    Next
    INDEX
    Explanations

    Interview text

    np_max-act · gemini-2.0-flash

    expressions related to personal experiences and reflections.

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

    The neuron detects polite expressions of thanks (e.g. “thank you for taking the time …”).

    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
     đơn
    -0.07
    Deque
    -0.06
    іп
    -0.06
     �
    -0.06
     прям
    -0.06
     мог
    -0.06
     merk
    -0.06
     ἐ
    -0.06
    138
    -0.06
    運
    -0.06
    POSITIVE LOGITS
    ENOMEM
    0.08
     indicative
    0.07
     oček
    0.07
    setDescription
    0.07
     añ
    0.07
     програми
    0.07
     moss
    0.07
     Experts
    0.07
     expires
    0.07
    BAR
    0.07
    Activations Density 0.091%

    No Known Activations