© 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. 44528
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on polite request markers, in particular the token “Please.”

    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
    Africa
    -0.07
     methodName
    -0.07
     Soviets
    -0.06
     redd
    -0.06
     snprintf
    -0.06
     Рус
    -0.06
     hips
    -0.06
    	check
    -0.06
    .CR
    -0.06
     sanity
    -0.06
    POSITIVE LOGITS
     merupakan
    0.07
    Việc
    0.07
     coppia
    0.07
     edilen
    0.06
    題
    0.06
    _Tis
    0.06
    _echo
    0.06
    願
    0.06
    _COORD
    0.06
     legislators
    0.06
    Activations Density 0.325%

    No Known Activations