© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9348
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    This neuron fires on the assistant’s standard “Can I help you…?” or “Is there anything else I can help you with?” type offers of further assistance.

    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
     وج
    -0.07
     th�
    -0.06
    šti
    -0.06
     ARM
    -0.06
     út
    -0.06
     GameState
    -0.06
    Su
    -0.06
    Nej
    -0.06
     Her
    -0.06
     تول
    -0.06
    POSITIVE LOGITS
    �除
    0.06
    stile
    0.06
     Pessoa
    0.06
     ~(
    0.06
     logits
    0.06
     плав
    0.06
     Fee
    0.06
    angible
    0.06
     ACCESS
    0.06
     recep
    0.06
    Activations Density 0.007%

    No Known Activations