© 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. 8745
    Prev
    Next
    INDEX
    Explanations

    needing more information

    np_max-act · gemini-2.0-flash

    requests for clarification or additional information.

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

    The neuron fires on the assistant’s requests for additional information or context (e.g. “I need more information,” “I need more context,” etc.).

    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
    .hour
    -0.07
    .xtext
    -0.07
    之间
    -0.06
    elts
    -0.06
    watch
    -0.06
    paint
    -0.06
     občan
    -0.06
    498
    -0.06
     avi
    -0.06
     arou
    -0.06
    POSITIVE LOGITS
     امروز
    0.06
     encuentra
    0.06
     changer
    0.06
    maktadır
    0.06
    .SELECT
    0.06
    	BYTE
    0.06
    �
    0.06
     istediğiniz
    0.06
    에도
    0.06
     pdb
    0.06
    Activations Density 0.041%

    No Known Activations