© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12376
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates specifically on the word “answer,” particularly when the assistant refers to knowing or not knowing an answer to a question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    responses that indicate a willingness to assist or provide information.

    oai_token-act-pair · gpt-4o-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
    賢
    -0.07
     Νο
    -0.07
     cest
    -0.07
    	body
    -0.07
    部屋
    -0.07
    .xz
    -0.06
    推荐
    -0.06
    oken
    -0.06
    _STATES
    -0.06
    ān
    -0.06
    POSITIVE LOGITS
    _api
    0.07
     alerts
    0.06
     cyber
    0.06
     chain
    0.06
     retired
    0.06
    name
    0.06
     RX
    0.06
     Feed
    0.06
                
    0.05
     التج
    0.05
    Activations Density 0.001%

    No Known Activations